reward -8.41846 time 10000.0 params 349.601 1 1 reward -7.29501 time 10000.0 params 419.601 1 1 reward -9.78671 time 10000.0 params 489.601 1 1 reward -5.39868 time 10000.0 params 384.601 1 1 reward -5.92649 time 10000.0 params 349.601 1 1 reward -5.96183 time 10000.0 params 367.101 1 1 reward -8.91839 time 10000.0 params 367.101 1 1 reward -8.80517 time 10000.0 params 402.101 1 1 reward -5.34759 time 10000.0 params 393.351 1 1 reward -7.84342 time 10000.0 params 402.101 1 1 reward -7.30352 time 10000.0 params 388.976 1 1 reward -7.34133 time 10000.0 params 388.976 1 1 reward -6.95393 time 10000.0 params 397.726 1 1 reward -6.85191 time 10000.0 params 395.538 1 1 reward -7.23333 time 10000.0 params 391.163 1 1 reward -7.16983 time 10000.0 params 394.444 1 1 reward -9.47194 time 10000.0 params 394.444 1 1 reward -4.94133 time 10000.0 params 392.257 1 1 reward -7.79592 time 10000.0 params 391.163 1 1 reward -8.30722 time 10000.0 params 391.163 1 1 reward -8.48987 time 10000.0 params 392.804 1 1 reward -7.35293 time 10000.0 params 392.804 1 1 reward -5.90904 time 10000.0 params 391.71 1 1 reward -6.44586 time 10000.0 params 391.984 1 1 reward -7.74954 time 10000.0 params 391.984 1 1 reward -8.22554 time 10000.0 params 392.53 1 1 reward -7.24915 time 10000.0 params 392.12 1 1 reward -6.69148 time 10000.0 params 349.601 1 1 reward -6.56252 time 10000.0 params 349.601 1 1 reward -7.90882 time 10000.0 params 419.601 1 1 reward -9.81900 time 10000.0 params 349.601 1 1 reward -9.63101 time 10000.0 params 489.601 1 1 reward -8.34204 time 10000.0 params 419.601 1 1 reward -10.82272 time 10000.0 params 384.601 1 1 reward -7.81410 time 10000.0 params 419.601 1 1 reward -6.04951 time 10000.0 params 349.601 1 1 reward -7.33024 time 10000.0 params 384.601 1 1 reward -5.55427 time 10000.0 params 367.101 1 1 reward -6.39678 time 10000.0 params 384.601 1 1 reward -7.54545 time 10000.0 params 367.101 1 1 reward -7.38125 time 10000.0 params 384.601 1 1 reward -5.01693 time 10000.0 params 402.101 1 1 reward -6.72744 time 10000.0 params 384.601 1 1 reward -7.94305 time 10000.0 params 393.351 1 1 reward -6.30354 time 10000.0 params 384.601 1 1 reward -7.11010 time 10000.0 params 402.101 1 1 reward -5.79948 time 10000.0 params 393.351 1 1 reward -8.10293 time 10000.0 params 388.976 1 1 reward -7.31844 time 10000.0 params 393.351 1 1 reward -6.75719 time 10000.0 params 388.976 1 1 reward -8.75978 time 10000.0 params 393.351 1 1 reward -6.10434 time 10000.0 params 397.726 1 1 reward -7.74751 time 10000.0 params 393.351 1 1 reward -5.89380 time 10000.0 params 395.538 1 1 reward -8.62314 time 10000.0 params 393.351 1 1 reward -8.26996 time 10000.0 params 391.163 1 1 reward -7.45173 time 10000.0 params 393.351 1 1 reward -10.74982 time 10000.0 params 394.444 1 1 reward -8.71541 time 10000.0 params 393.351 1 1 reward -6.82101 time 10000.0 params 394.444 1 1 reward -4.92241 time 10000.0 params 393.351 1 1 reward -6.76712 time 10000.0 params 392.257 1 1 reward -8.33139 time 10000.0 params 393.351 1 1 reward -8.45912 time 10000.0 params 391.163 1 1 reward -7.35963 time 10000.0 params 392.257 1 1 reward -7.84547 time 10000.0 params 391.163 1 1 reward -5.87824 time 10000.0 params 392.257 1 1 reward -8.25776 time 10000.0 params 392.804 1 1 reward -6.27649 time 10000.0 params 392.257 1 1 reward -5.38457 time 10000.0 params 392.804 1 1 reward -7.84926 time 10000.0 params 392.257 1 1 reward -6.98162 time 10000.0 params 391.71 1 1 reward -2.91270 time 10000.0 params 392.257 1 1 reward -8.18677 time 10000.0 params 391.984 1 1 reward -7.87232 time 10000.0 params 392.257 1 1 reward -5.17744 time 10000.0 params 350 1 1 reward -8.34330 time 10000.0 params 350 1 1 reward -8.30396 time 10000.0 params 350 1 1 reward -15.60749 time 10000.0 params 0 1 1 reward -11.84330 time 10000.0 params 7.82425 1 1 reward -11.95684 time 10000.0 params 7.82425 1 1 reward -8.04516 time 10000.0 params 529.002 1 1 reward -9.57000 time 10000.0 params 683.154 1 1 reward -9.14182 time 10000.0 params 683.154 1 1 reward -9.69671 time 10000.0 params 452.196 1 1 reward -10.11374 time 10000.0 params 449.513 1 1 reward -5.13808 time 10000.0 params 449.513 1 1 reward -8.43143 time 10000.0 params 422.837 1 1 reward -9.25991 time 10000.0 params 423.814 1 1 reward -9.71616 time 10000.0 params 423.814 1 1 reward -7.20831 time 10000.0 params 448.714 1 1 reward -1.35117 time 10000.0 params 166.604 1 1 reward -0.03230 time 10000.0 params 166.604 1 1 reward -1.45843 time 10000.0 params 242.165 1 1 reward -10.04456 time 10000.0 params 574.788 1 1 reward -8.06297 time 10000.0 params 574.788 1 1 reward -2.21912 time 10000.0 params 242.165 1 1 reward -2.93038 time 10000.0 params 246.434 1 1 reward -5.71954 time 10000.0 params 246.434 1 1 reward -1.36205 time 10000.0 params 166.604 1 1 reward -2.24205 time 10000.0 params 57.6059 1 1 reward -2.26559 time 10000.0 params 57.6059 1 1 reward -1.61984 time 10000.0 params 179.165 1 1 reward -1.59108 time 10000.0 params 180.219 1 1 reward -2.20733 time 10000.0 params 180.219 1 1 reward 0.09434 time 10000.0 params 128.076 1 1 reward 0.18540 time 10000.0 params 100.634 1 1 reward -0.31746 time 10000.0 params 100.634 1 1 reward 0.97798 time 10000.0 params 123.807 1 1 reward -1.53655 time 10000.0 params 118.063 1 1 reward 0.79158 time 10000.0 params 118.063 1 1 reward -0.16980 time 10000.0 params 134.321 1 1 reward -3.47130 time 10000.0 params 219.106 1 1 reward -1.58302 time 10000.0 params 219.106 1 1 reward -1.17526 time 10000.0 params 134.321 1 1 reward -0.52050 time 10000.0 params 143.091 1 1 reward -1.40384 time 10000.0 params 143.091 1 1 reward 0.01320 time 10000.0 params 121.851 1 1 reward -0.49496 time 10000.0 params 85.5914 1 1 reward -0.89821 time 10000.0 params 85.5914 1 1 reward 0.04830 time 10000.0 params 123.233 1 1 reward 0.74152 time 10000.0 params 211.22 1 1 reward -0.38290 time 10000.0 params 211.22 1 1 reward -0.00060 time 10000.0 params 123.233 1 1 reward -0.55719 time 10000.0 params 133.347 1 1 reward -0.63603 time 10000.0 params 133.347 1 1 reward 0.26986 time 10000.0 params 116.771 1 1 reward -1.10021 time 10000.0 params 116.369 1 1 reward -0.16950 time 10000.0 params 116.369 1 1 reward -0.13180 time 10000.0 params 115.604 1 1 reward 0.05718 time 10000.0 params 126.906 1 1 reward -0.35350 time 10000.0 params 126.906 1 1 reward -1.66090 time 10000.0 params 113.962 1 1 reward -0.25829 time 10000.0 params 101.5 1 1 reward -1.62770 time 10000.0 params 101.5 1 1 reward -1.14034 time 10000.0 params 116.369 1 1 reward 0.16403 time 10000.0 params 98.0572 1 1 reward 0.07087 time 10000.0 params 98.0572 1 1 reward 0.27117 time 10000.0 params 116.369 1 1 reward -1.49004 time 10000.0 params 159.649 1 1 reward -0.54350 time 10000.0 params 159.649 1 1 reward 0.40305 time 10000.0 params 119.815 1 1 reward 0.09586 time 10000.0 params 111.969 1 1 reward -0.79231 time 10000.0 params 111.969 1 1 reward -0.97717 time 10000.0 params 120.326 1 1 reward -0.86410 time 10000.0 params 97.7614 1 1 reward -0.37620 time 10000.0 params 97.7614 1 1 reward -3.73557 time 10000.0 params 349.601 1 1 reward -1.97029 time 10000.0 params 419.601 1 1 reward -5.38998 time 10000.0 params 489.601 1 1 reward -5.66867 time 10000.0 params 384.601 1 1 reward -1.17947 time 10000.0 params 384.601 1 1 reward -3.21878 time 10000.0 params 349.601 1 1 reward -4.36025 time 10000.0 params 402.101 1 1 reward -4.25496 time 10000.0 params 402.101 1 1 reward -2.30765 time 10000.0 params 367.101 1 1 reward -2.86169 time 10000.0 params 375.851 1 1 reward -4.09849 time 10000.0 params 375.851 1 1 reward -3.87078 time 10000.0 params 393.351 1 1 reward -3.15888 time 10000.0 params 388.976 1 1 reward -1.56382 time 10000.0 params 380.226 1 1 reward -2.86724 time 10000.0 params 382.413 1 1 reward -3.28910 time 10000.0 params 382.413 1 1 reward -3.73470 time 10000.0 params 386.788 1 1 reward -1.57244 time 10000.0 params 383.507 1 1 reward -3.56244 time 10000.0 params 385.694 1 1 reward -3.02266 time 10000.0 params 384.054 1 1 reward 0.19529 time 10000.0 params 384.054 1 1 reward -1.72137 time 10000.0 params 383.507 1 1 reward -2.68299 time 10000.0 params 384.327 1 1 reward -4.95584 time 10000.0 params 384.327 1 1 reward -3.08475 time 10000.0 params 383.78 1 1 reward -2.90092 time 10000.0 params 383.917 1 1 reward -4.13397 time 10000.0 params 384.191 1 1 reward -3.96914 time 10000.0 params 383.985 1 1 reward -3.48188 time 10000.0 params 383.985 1 1 reward -2.69119 time 10000.0 params 349.601 1 1 reward -2.52123 time 10000.0 params 349.601 1 1 reward -2.45808 time 10000.0 params 419.601 1 1 reward -2.12540 time 10000.0 params 349.601 1 1 reward -5.78298 time 10000.0 params 489.601 1 1 reward -4.77623 time 10000.0 params 419.601 1 1 reward -2.45087 time 10000.0 params 384.601 1 1 reward -2.66025 time 10000.0 params 419.601 1 1 reward -2.50431 time 10000.0 params 384.601 1 1 reward -5.87065 time 10000.0 params 419.601 1 1 reward -1.31750 time 10000.0 params 349.601 1 1 reward -5.24093 time 10000.0 params 384.601 1 1 reward 1.01020 time 10000.0 params 402.101 1 1 reward -1.49822 time 10000.0 params 384.601 1 1 reward -3.86282 time 10000.0 params 402.101 1 1 reward -2.08879 time 10000.0 params 384.601 1 1 reward -3.89272 time 10000.0 params 367.101 1 1 reward -4.38312 time 10000.0 params 384.601 1 1 reward -0.88409 time 10000.0 params 375.851 1 1 reward -3.91629 time 10000.0 params 384.601 1 1 reward -1.16206 time 10000.0 params 375.851 1 1 reward -2.92694 time 10000.0 params 384.601 1 1 reward -1.72118 time 10000.0 params 393.351 1 1 reward -3.12383 time 10000.0 params 384.601 1 1 reward -3.44367 time 10000.0 params 388.976 1 1 reward -3.30238 time 10000.0 params 384.601 1 1 reward -3.29527 time 10000.0 params 380.226 1 1 reward -0.73103 time 10000.0 params 384.601 1 1 reward -3.46026 time 10000.0 params 382.413 1 1 reward -4.51656 time 10000.0 params 384.601 1 1 reward -4.71947 time 10000.0 params 382.413 1 1 reward -1.88053 time 10000.0 params 384.601 1 1 reward -6.76431 time 10000.0 params 386.788 1 1 reward -3.92027 time 10000.0 params 384.601 1 1 reward -6.31563 time 10000.0 params 383.507 1 1 reward -4.14049 time 10000.0 params 384.601 1 1 reward -1.35730 time 10000.0 params 385.694 1 1 reward -2.42750 time 10000.0 params 384.601 1 1 reward -3.94251 time 10000.0 params 384.054 1 1 reward -4.43118 time 10000.0 params 384.601 1 1 reward -3.63098 time 10000.0 params 384.054 1 1 reward -3.03663 time 10000.0 params 384.601 1 1 reward -2.16375 time 10000.0 params 383.507 1 1 reward -2.18738 time 10000.0 params 384.054 1 1 reward -3.16551 time 10000.0 params 384.327 1 1 reward -3.86651 time 10000.0 params 384.054 1 1 reward -0.64617 time 10000.0 params 384.327 1 1 reward -2.23344 time 10000.0 params 384.054 1 1 reward 0.28379 time 10000.0 params 350 1 1 reward -2.52833 time 10000.0 params 350 1 1 reward -5.02528 time 10000.0 params 350 1 1 reward -16.02992 time 10000.0 params 0 1 1 reward -13.95676 time 10000.0 params 3.10098 1 1 reward -13.74849 time 10000.0 params 3.10098 1 1 reward -4.55718 time 10000.0 params 331.032 1 1 reward -6.32765 time 10000.0 params 681.278 1 1 reward -4.44094 time 10000.0 params 681.278 1 1 reward -5.20997 time 10000.0 params 541.219 1 1 reward 1.72627 time 10000.0 params 181.403 1 1 reward 3.86298 time 10000.0 params 181.403 1 1 reward -3.14603 time 10000.0 params 400.414 1 1 reward -5.44530 time 10000.0 params 530.124 1 1 reward -6.71599 time 10000.0 params 530.124 1 1 reward 3.76800 time 10000.0 params 181.403 1 1 reward -3.86961 time 10000.0 params 26.2762 1 1 reward -4.01190 time 10000.0 params 26.2762 1 1 reward -2.08493 time 10000.0 params 356.366 1 1 reward -3.37945 time 10000.0 params 358.263 1 1 reward -1.11980 time 10000.0 params 358.263 1 1 reward 4.11590 time 10000.0 params 195.731 1 1 reward -3.98044 time 10000.0 params 443.759 1 1 reward -3.52170 time 10000.0 params 443.759 1 1 reward 3.30467 time 10000.0 params 195.731 1 1 reward 0.50035 time 10000.0 params 263.752 1 1 reward -0.55389 time 10000.0 params 263.752 1 1 reward 2.47285 time 10000.0 params 193.081 1 1 reward 1.67588 time 10000.0 params 197.852 1 1 reward 4.39026 time 10000.0 params 197.852 1 1 reward 3.30473 time 10000.0 params 160.839 1 1 reward 2.14283 time 10000.0 params 156.759 1 1 reward 2.54458 time 10000.0 params 156.759 1 1 reward 1.24645 time 10000.0 params 197.195 1 1 reward 2.60474 time 10000.0 params 203.196 1 1 reward 1.65889 time 10000.0 params 203.196 1 1 reward 2.20870 time 10000.0 params 179.939 1 1 reward 4.00480 time 10000.0 params 184.223 1 1 reward 4.83462 time 10000.0 params 184.223 1 1 reward 1.74743 time 10000.0 params 179.876 1 1 reward 3.17572 time 10000.0 params 177.827 1 1 reward 2.04414 time 10000.0 params 177.827 1 1 reward 2.62255 time 10000.0 params 190.327 1 1 reward 2.97285 time 10000.0 params 186.11 1 1 reward 3.43591 time 10000.0 params 186.11 1 1 reward 4.73157 time 10000.0 params 190.239 1 1 reward -0.30550 time 10000.0 params 223.835 1 1 reward 1.03769 time 10000.0 params 223.835 1 1 reward 2.59574 time 10000.0 params 191.783 1 1 reward 3.10573 time 10000.0 params 166.472 1 1 reward 4.38385 time 10000.0 params 166.472 1 1 reward 5.01823 time 10000.0 params 191.783 1 1 reward 1.24819 time 10000.0 params 200.313 1 1 reward 3.47836 time 10000.0 params 200.313 1 1 reward 3.36232 time 10000.0 params 191.153 1 1 reward 1.57900 time 10000.0 params 200.17 1 1 reward 0.56287 time 10000.0 params 200.17 1 1 reward 4.19472 time 10000.0 params 191.783 1 1 reward 0.98107 time 10000.0 params 194.575 1 1 reward -0.78674 time 10000.0 params 194.575 1 1 reward 0.00980 time 10000.0 params 183.109 1 1 reward 5.46807 time 10000.0 params 171.175 1 1 reward 2.78010 time 10000.0 params 171.175 1 1 reward 3.83899 time 10000.0 params 183.109 1 1 reward 1.10800 time 10000.0 params 196.967 1 1 reward 2.70723 time 10000.0 params 196.967 1 1 reward 4.52909 time 10000.0 params 183.109 1 1 reward 3.09437 time 10000.0 params 193.326 1 1 reward 1.69270 time 10000.0 params 193.326 1 1 reward 2.91354 time 10000.0 params 183.109 1 1 reward 3.06157 time 10000.0 params 198.643 1 1 reward 2.41552 time 10000.0 params 198.643 1 1 reward 2.19695 time 10000.0 params 349.601 0.517353 0.517353 reward 4.28583 time 10000.0 params 419.601 0.417353 0.417353 reward 3.84951 time 10000.0 params 419.601 0.517353 0.517353 reward 3.54755 time 10000.0 params 489.601 0.417353 0.417353 reward 1.29109 time 10000.0 params 454.601 0.442353 0.442353 reward 3.30087 time 10000.0 params 454.601 0.417353 0.417353 reward 2.97424 time 10000.0 params 419.601 0.467353 0.467353 reward 3.86061 time 10000.0 params 454.601 0.367353 0.367353 reward 1.45886 time 10000.0 params 419.601 0.367353 0.367353 reward 4.07549 time 10000.0 params 445.851 0.404853 0.404853 reward 2.87770 time 10000.0 params 410.851 0.454853 0.454853 reward 4.06919 time 10000.0 params 443.663 0.389228 0.389228 reward 3.03038 time 10000.0 params 421.788 0.432978 0.432978 reward 3.64202 time 10000.0 params 438.194 0.400166 0.400166 reward 4.72380 time 10000.0 params 432.726 0.411103 0.411103 reward 1.71153 time 10000.0 params 431.632 0.403291 0.403291 reward 3.34922 time 10000.0 params 420.694 0.425166 0.425166 reward 4.61654 time 10000.0 params 423.429 0.419697 0.419697 reward 1.89566 time 10000.0 params 436.554 0.413447 0.413447 reward 2.13812 time 10000.0 params 423.839 0.416377 0.416377 reward 2.70590 time 10000.0 params 426.163 0.414228 0.414228 reward 3.78410 time 10000.0 params 428.077 0.4154 0.4154 reward 2.45898 time 10000.0 params 434.64 0.412275 0.412275 reward 4.61921 time 10000.0 params 428.282 0.41374 0.41374 reward 3.63622 time 10000.0 params 432.931 0.409443 0.409443 reward 3.74666 time 10000.0 params 429.291 0.413911 0.413911 reward 3.20567 time 10000.0 params 430.504 0.412422 0.412422 reward 1.20619 time 10000.0 params 430.401 0.413252 0.413252 reward 1.42978 time 10000.0 params 432.828 0.410273 0.410273 reward 2.38697 time 10000.0 params 432.222 0.411018 0.411018 reward 3.12895 time 10000.0 params 431.008 0.412507 0.412507 reward 4.13003 time 10000.0 params 431.312 0.412135 0.412135 reward 2.68949 time 10000.0 params 433.533 0.410817 0.410817 reward 2.21388 time 10000.0 params 431.261 0.41202 0.41202 reward 1.60536 time 10000.0 params 431.615 0.411763 0.411763 reward 3.77467 time 10000.0 params 432.019 0.411619 0.411619 reward 4.21359 time 10000.0 params 433.129 0.41096 0.41096 reward 1.70796 time 10000.0 params 433.837 0.410444 0.410444 reward 3.73067 time 10000.0 params 432.473 0.411325 0.411325 reward 4.68519 time 10000.0 params 432.928 0.411032 0.411032 reward 5.28110 time 10000.0 params 432.372 0.411361 0.411361 reward 2.64680 time 10000.0 params 432.17 0.411433 0.411433 reward 3.17179 time 10000.0 params 432.738 0.411132 0.411132 reward 3.76616 time 10000.0 params 432.549 0.411232 0.411232 reward 5.18778 time 10000.0 params 432.65 0.411196 0.411196 reward 3.81554 time 10000.0 params 349.601 0.517353 0.517353 reward 0.70720 time 10000.0 params 349.601 0.517353 0.517353 reward 2.27863 time 10000.0 params 419.601 0.417353 0.417353 reward 1.66953 time 10000.0 params 349.601 0.517353 0.517353 reward 3.45066 time 10000.0 params 419.601 0.517353 0.517353 reward 3.44790 time 10000.0 params 419.601 0.417353 0.417353 reward 3.65557 time 10000.0 params 489.601 0.417353 0.417353 reward 4.65586 time 10000.0 params 419.601 0.417353 0.417353 reward 2.06563 time 10000.0 params 454.601 0.442353 0.442353 reward 2.53292 time 10000.0 params 419.601 0.417353 0.417353 reward 1.19016 time 10000.0 params 454.601 0.417353 0.417353 reward 2.30094 time 10000.0 params 419.601 0.417353 0.417353 reward 1.10698 time 10000.0 params 419.601 0.467353 0.467353 reward 4.21012 time 10000.0 params 419.601 0.417353 0.417353 reward 1.65133 time 10000.0 params 454.601 0.367353 0.367353 reward 1.99403 time 10000.0 params 419.601 0.417353 0.417353 reward 2.66124 time 10000.0 params 419.601 0.367353 0.367353 reward -1.33356 time 10000.0 params 419.601 0.417353 0.417353 reward 4.29740 time 10000.0 params 445.851 0.404853 0.404853 reward 4.00016 time 10000.0 params 419.601 0.417353 0.417353 reward 2.08398 time 10000.0 params 410.851 0.454853 0.454853 reward 3.12878 time 10000.0 params 419.601 0.417353 0.417353 reward 3.70425 time 10000.0 params 443.663 0.389228 0.389228 reward 4.04204 time 10000.0 params 419.601 0.417353 0.417353 reward 3.14323 time 10000.0 params 421.788 0.432978 0.432978 reward 2.38029 time 10000.0 params 419.601 0.417353 0.417353 reward 0.84340 time 10000.0 params 438.194 0.400166 0.400166 reward 2.77516 time 10000.0 params 419.601 0.417353 0.417353 reward 3.66528 time 10000.0 params 432.726 0.411103 0.411103 reward 4.19071 time 10000.0 params 419.601 0.417353 0.417353 reward 5.68798 time 10000.0 params 431.632 0.403291 0.403291 reward 3.64310 time 10000.0 params 432.726 0.411103 0.411103 reward 3.57897 time 10000.0 params 420.694 0.425166 0.425166 reward 2.75138 time 10000.0 params 432.726 0.411103 0.411103 reward 6.17933 time 10000.0 params 423.429 0.419697 0.419697 reward 2.78938 time 10000.0 params 432.726 0.411103 0.411103 reward 2.81645 time 10000.0 params 436.554 0.413447 0.413447 reward 4.06098 time 10000.0 params 432.726 0.411103 0.411103 reward 4.02499 time 10000.0 params 423.839 0.416377 0.416377 reward 4.13290 time 10000.0 params 432.726 0.411103 0.411103 reward 2.23517 time 10000.0 params 426.163 0.414228 0.414228 reward 4.78688 time 10000.0 params 432.726 0.411103 0.411103 reward 2.39879 time 10000.0 params 428.077 0.4154 0.4154 reward 2.55989 time 10000.0 params 432.726 0.411103 0.411103 reward 3.20698 time 10000.0 params 434.64 0.412275 0.412275 reward 2.41865 time 10000.0 params 432.726 0.411103 0.411103 reward 3.71320 time 10000.0 params 428.282 0.41374 0.41374 reward 2.31686 time 10000.0 params 432.726 0.411103 0.411103 reward 0.87311 time 10000.0 params 432.931 0.409443 0.409443 reward 2.16280 time 10000.0 params 432.726 0.411103 0.411103 reward 1.71085 time 10000.0 params 429.291 0.413911 0.413911 reward 4.29068 time 10000.0 params 432.726 0.411103 0.411103 reward 3.17579 time 10000.0 params 430.504 0.412422 0.412422 reward 1.38337 time 10000.0 params 432.726 0.411103 0.411103 reward 3.93013 time 10000.0 params 430.401 0.413252 0.413252 reward 2.32740 time 10000.0 params 432.726 0.411103 0.411103 reward 1.30320 time 10000.0 params 432.828 0.410273 0.410273 reward 4.23875 time 10000.0 params 432.726 0.411103 0.411103 reward 2.66851 time 10000.0 params 432.222 0.411018 0.411018 reward 2.41585 time 10000.0 params 432.726 0.411103 0.411103 reward 2.42697 time 10000.0 params 431.008 0.412507 0.412507 reward 2.96474 time 10000.0 params 432.726 0.411103 0.411103 reward 3.29372 time 10000.0 params 431.312 0.412135 0.412135 reward 1.13659 time 10000.0 params 432.726 0.411103 0.411103 reward 0.68351 time 10000.0 params 433.533 0.410817 0.410817 reward 3.10938 time 10000.0 params 432.726 0.411103 0.411103 reward 3.35107 time 10000.0 params 431.261 0.41202 0.41202 reward 1.21837 time 10000.0 params 432.726 0.411103 0.411103 reward 0.38755 time 10000.0 params 431.615 0.411763 0.411763 reward 3.80704 time 10000.0 params 432.726 0.411103 0.411103 reward 2.64194 time 10000.0 params 432.019 0.411619 0.411619 reward 3.23064 time 10000.0 params 432.726 0.411103 0.411103 reward 1.88343 time 10000.0 params 433.129 0.41096 0.41096 reward 3.27973 time 10000.0 params 432.726 0.411103 0.411103 reward 2.39456 time 10000.0 params 433.837 0.410444 0.410444 reward 3.26027 time 10000.0 params 432.726 0.411103 0.411103 reward 2.39838 time 10000.0 params 432.473 0.411325 0.411325 reward 3.71492 time 10000.0 params 432.726 0.411103 0.411103 reward 3.26976 time 10000.0 params 432.928 0.411032 0.411032 reward 4.53010 time 10000.0 params 432.726 0.411103 0.411103 reward 2.19695 time 10000.0 params 349.601 0.517353 0.517353 reward 4.28583 time 10000.0 params 419.601 0.417353 0.417353 reward 3.84951 time 10000.0 params 419.601 0.517353 0.517353 reward 3.54755 time 10000.0 params 489.601 0.417353 0.417353 reward 1.29109 time 10000.0 params 454.601 0.442353 0.442353 reward 3.30087 time 10000.0 params 454.601 0.417353 0.417353 reward 2.97424 time 10000.0 params 419.601 0.467353 0.467353 reward 3.86061 time 10000.0 params 454.601 0.367353 0.367353 reward 1.45886 time 10000.0 params 419.601 0.367353 0.367353 reward 4.07549 time 10000.0 params 445.851 0.404853 0.404853 reward 2.87770 time 10000.0 params 410.851 0.454853 0.454853 reward 4.06919 time 10000.0 params 443.663 0.389228 0.389228 reward 3.03038 time 10000.0 params 421.788 0.432978 0.432978 reward 3.64202 time 10000.0 params 438.194 0.400166 0.400166 reward 4.72380 time 10000.0 params 432.726 0.411103 0.411103 reward 1.71153 time 10000.0 params 431.632 0.403291 0.403291 reward 3.34922 time 10000.0 params 420.694 0.425166 0.425166 reward 4.61654 time 10000.0 params 423.429 0.419697 0.419697 reward 1.89566 time 10000.0 params 436.554 0.413447 0.413447 reward 2.13812 time 10000.0 params 423.839 0.416377 0.416377 reward 2.70590 time 10000.0 params 426.163 0.414228 0.414228 reward 3.78410 time 10000.0 params 428.077 0.4154 0.4154 reward 2.45898 time 10000.0 params 434.64 0.412275 0.412275 reward 4.61921 time 10000.0 params 428.282 0.41374 0.41374 reward 3.63622 time 10000.0 params 432.931 0.409443 0.409443 reward 3.74666 time 10000.0 params 429.291 0.413911 0.413911 reward 3.20567 time 10000.0 params 430.504 0.412422 0.412422 reward 1.20619 time 10000.0 params 430.401 0.413252 0.413252 reward 1.42978 time 10000.0 params 432.828 0.410273 0.410273 reward 2.38697 time 10000.0 params 432.222 0.411018 0.411018 reward 3.12895 time 10000.0 params 431.008 0.412507 0.412507 reward 4.13003 time 10000.0 params 431.312 0.412135 0.412135 reward 2.68949 time 10000.0 params 433.533 0.410817 0.410817 reward 2.21388 time 10000.0 params 431.261 0.41202 0.41202 reward 1.60536 time 10000.0 params 431.615 0.411763 0.411763 reward 3.77467 time 10000.0 params 432.019 0.411619 0.411619 reward 4.21359 time 10000.0 params 433.129 0.41096 0.41096 reward 1.70796 time 10000.0 params 433.837 0.410444 0.410444 reward 3.73067 time 10000.0 params 432.473 0.411325 0.411325 reward 4.68519 time 10000.0 params 432.928 0.411032 0.411032 reward 5.28110 time 10000.0 params 432.372 0.411361 0.411361 reward 2.64680 time 10000.0 params 432.17 0.411433 0.411433 reward 3.17179 time 10000.0 params 432.738 0.411132 0.411132 reward 3.76616 time 10000.0 params 432.549 0.411232 0.411232 reward 5.18778 time 10000.0 params 432.65 0.411196 0.411196 reward 3.81554 time 10000.0 params 349.601 0.517353 0.517353 reward 0.70720 time 10000.0 params 349.601 0.517353 0.517353 reward 2.27863 time 10000.0 params 419.601 0.417353 0.417353 reward 1.66953 time 10000.0 params 349.601 0.517353 0.517353 reward 3.45066 time 10000.0 params 419.601 0.517353 0.517353 reward 3.44790 time 10000.0 params 419.601 0.417353 0.417353 reward 3.65557 time 10000.0 params 489.601 0.417353 0.417353 reward 4.65586 time 10000.0 params 419.601 0.417353 0.417353 reward 2.06563 time 10000.0 params 454.601 0.442353 0.442353 reward 2.53292 time 10000.0 params 419.601 0.417353 0.417353 reward 1.19016 time 10000.0 params 454.601 0.417353 0.417353 reward 2.30094 time 10000.0 params 419.601 0.417353 0.417353 reward 1.10698 time 10000.0 params 419.601 0.467353 0.467353 reward 4.21012 time 10000.0 params 419.601 0.417353 0.417353 reward 1.65133 time 10000.0 params 454.601 0.367353 0.367353 reward 1.99403 time 10000.0 params 419.601 0.417353 0.417353 reward 2.66124 time 10000.0 params 419.601 0.367353 0.367353 reward -1.33356 time 10000.0 params 419.601 0.417353 0.417353 reward 4.29740 time 10000.0 params 445.851 0.404853 0.404853 reward 4.00016 time 10000.0 params 419.601 0.417353 0.417353 reward 2.08398 time 10000.0 params 410.851 0.454853 0.454853 reward 3.12878 time 10000.0 params 419.601 0.417353 0.417353 reward 3.70425 time 10000.0 params 443.663 0.389228 0.389228 reward 4.04204 time 10000.0 params 419.601 0.417353 0.417353 reward 3.14323 time 10000.0 params 421.788 0.432978 0.432978 reward 2.38029 time 10000.0 params 419.601 0.417353 0.417353 reward 0.84340 time 10000.0 params 438.194 0.400166 0.400166 reward 2.77516 time 10000.0 params 419.601 0.417353 0.417353 reward 3.66528 time 10000.0 params 432.726 0.411103 0.411103 reward 4.19071 time 10000.0 params 419.601 0.417353 0.417353 reward 5.68798 time 10000.0 params 431.632 0.403291 0.403291 reward 3.64310 time 10000.0 params 432.726 0.411103 0.411103 reward 3.57897 time 10000.0 params 420.694 0.425166 0.425166 reward 2.75138 time 10000.0 params 432.726 0.411103 0.411103 reward 6.17933 time 10000.0 params 423.429 0.419697 0.419697 reward 2.78938 time 10000.0 params 432.726 0.411103 0.411103 reward 2.81645 time 10000.0 params 436.554 0.413447 0.413447 reward 4.06098 time 10000.0 params 432.726 0.411103 0.411103 reward 4.02499 time 10000.0 params 423.839 0.416377 0.416377 reward 4.13290 time 10000.0 params 432.726 0.411103 0.411103 reward 2.23517 time 10000.0 params 426.163 0.414228 0.414228 reward 4.78688 time 10000.0 params 432.726 0.411103 0.411103 reward 2.39879 time 10000.0 params 428.077 0.4154 0.4154 reward 2.55989 time 10000.0 params 432.726 0.411103 0.411103 reward 3.20698 time 10000.0 params 434.64 0.412275 0.412275 reward 2.41865 time 10000.0 params 432.726 0.411103 0.411103 reward 3.71320 time 10000.0 params 428.282 0.41374 0.41374 reward 2.31686 time 10000.0 params 432.726 0.411103 0.411103 reward 0.87311 time 10000.0 params 432.931 0.409443 0.409443 reward 2.16280 time 10000.0 params 432.726 0.411103 0.411103 reward 1.71085 time 10000.0 params 429.291 0.413911 0.413911 reward 4.29068 time 10000.0 params 432.726 0.411103 0.411103 reward 3.17579 time 10000.0 params 430.504 0.412422 0.412422 reward 1.38337 time 10000.0 params 432.726 0.411103 0.411103 reward 3.93013 time 10000.0 params 430.401 0.413252 0.413252 reward 2.32740 time 10000.0 params 432.726 0.411103 0.411103 reward 1.30320 time 10000.0 params 432.828 0.410273 0.410273 reward 4.23875 time 10000.0 params 432.726 0.411103 0.411103 reward 2.66851 time 10000.0 params 432.222 0.411018 0.411018 reward 2.41585 time 10000.0 params 432.726 0.411103 0.411103 reward 2.42697 time 10000.0 params 431.008 0.412507 0.412507 reward 2.96474 time 10000.0 params 432.726 0.411103 0.411103 reward 3.29372 time 10000.0 params 431.312 0.412135 0.412135 reward 1.13659 time 10000.0 params 432.726 0.411103 0.411103 reward 0.68351 time 10000.0 params 433.533 0.410817 0.410817 reward 3.10938 time 10000.0 params 432.726 0.411103 0.411103 reward 3.35107 time 10000.0 params 431.261 0.41202 0.41202 reward 1.21837 time 10000.0 params 432.726 0.411103 0.411103 reward 0.38755 time 10000.0 params 431.615 0.411763 0.411763 reward 3.80704 time 10000.0 params 432.726 0.411103 0.411103 reward 2.64194 time 10000.0 params 432.019 0.411619 0.411619 reward 3.23064 time 10000.0 params 432.726 0.411103 0.411103 reward 1.88343 time 10000.0 params 433.129 0.41096 0.41096 reward 3.27973 time 10000.0 params 432.726 0.411103 0.411103 reward 2.39456 time 10000.0 params 433.837 0.410444 0.410444 reward 3.26027 time 10000.0 params 432.726 0.411103 0.411103 reward 2.39838 time 10000.0 params 432.473 0.411325 0.411325 reward 3.71492 time 10000.0 params 432.726 0.411103 0.411103 reward 3.26976 time 10000.0 params 432.928 0.411032 0.411032 reward 4.53010 time 10000.0 params 432.726 0.411103 0.411103 reward 4.17559 time 10000.0 params 331.673 0.407246 0.407246 reward 3.52826 time 10000.0 params 261.673 0.507246 0.507246 reward 4.06028 time 10000.0 params 261.673 0.407246 0.407246 reward 2.81243 time 10000.0 params 331.673 0.307246 0.307246 reward 4.07489 time 10000.0 params 279.173 0.457246 0.457246 reward 3.22305 time 10000.0 params 349.173 0.457246 0.457246 reward 3.12226 time 10000.0 params 283.548 0.419746 0.419746 reward 3.92653 time 10000.0 params 305.423 0.432246 0.432246 reward 4.16466 time 10000.0 params 296.673 0.407246 0.407246 reward 4.75029 time 10000.0 params 322.923 0.382246 0.382246 reward 4.06449 time 10000.0 params 331.673 0.357246 0.357246 reward 4.04999 time 10000.0 params 357.923 0.382246 0.382246 reward 4.25497 time 10000.0 params 311.985 0.400996 0.400996 reward 2.49883 time 10000.0 params 303.235 0.375996 0.375996 reward 3.36489 time 10000.0 params 324.563 0.399434 0.399434 reward 3.88000 time 10000.0 params 327.298 0.394746 0.394746 reward 3.21086 time 10000.0 params 317.454 0.391621 0.391621 reward 4.28900 time 10000.0 params 332.766 0.385371 0.385371 reward 1.85355 time 10000.0 params 328.391 0.372871 0.372871 reward 4.18233 time 10000.0 params 327.571 0.389277 0.389277 reward 4.10524 time 10000.0 params 328.118 0.37834 0.37834 reward 1.49845 time 10000.0 params 327.708 0.386543 0.386543 reward 5.11745 time 10000.0 params 325.247 0.385762 0.385762 reward 3.74730 time 10000.0 params 327.844 0.383809 0.383809 reward 2.16668 time 10000.0 params 320.325 0.384199 0.384199 reward 3.82705 time 10000.0 params 325.965 0.383906 0.383906 reward 3.66999 time 10000.0 params 322.205 0.384102 0.384102 reward 4.74462 time 10000.0 params 325.025 0.383955 0.383955 reward 4.24145 time 10000.0 params 323.145 0.384053 0.384053 reward 4.22068 time 10000.0 params 324.555 0.383979 0.383979 reward 2.43711 time 10000.0 params 324.085 0.384004 0.384004 reward 4.76818 time 10000.0 params 325.136 0.384858 0.384858 reward 2.92338 time 10000.0 params 326.298 0.386616 0.386616 reward 3.16669 time 10000.0 params 325.744 0.385963 0.385963 reward 4.35132 time 10000.0 params 324.638 0.384657 0.384657 reward 2.70736 time 10000.0 params 324.915 0.384984 0.384984 reward 3.40865 time 10000.0 params 324.942 0.385209 0.385209 reward 4.78480 time 10000.0 params 325.191 0.38531 0.38531 reward 3.71740 time 10000.0 params 325.496 0.385862 0.385862 reward 4.72067 time 10000.0 params 325.357 0.385699 0.385699 reward 2.88583 time 10000.0 params 325.081 0.385373 0.385373 reward 3.28107 time 10000.0 params 325.288 0.385618 0.385618 reward 3.82178 time 10000.0 params 325.302 0.38573 0.38573 reward 4.79651 time 10000.0 params 325.219 0.385536 0.385536 reward 4.62472 time 10000.0 params 331.673 0.407246 0.407246 reward 3.71949 time 10000.0 params 331.673 0.407246 0.407246 reward 2.18412 time 10000.0 params 261.673 0.507246 0.507246 reward 3.63974 time 10000.0 params 331.673 0.407246 0.407246 reward 2.95860 time 10000.0 params 261.673 0.407246 0.407246 reward 4.55714 time 10000.0 params 331.673 0.407246 0.407246 reward 3.81061 time 10000.0 params 331.673 0.307246 0.307246 reward 4.14305 time 10000.0 params 331.673 0.407246 0.407246 reward 2.96876 time 10000.0 params 279.173 0.457246 0.457246 reward 2.62616 time 10000.0 params 331.673 0.407246 0.407246 reward 2.94155 time 10000.0 params 349.173 0.457246 0.457246 reward 4.18729 time 10000.0 params 331.673 0.407246 0.407246 reward 3.13907 time 10000.0 params 283.548 0.419746 0.419746 reward 5.42581 time 10000.0 params 331.673 0.407246 0.407246 reward 4.13327 time 10000.0 params 305.423 0.432246 0.432246 reward 5.02939 time 10000.0 params 331.673 0.407246 0.407246 reward 3.61572 time 10000.0 params 296.673 0.407246 0.407246 reward 2.35093 time 10000.0 params 331.673 0.407246 0.407246 reward 4.13258 time 10000.0 params 322.923 0.382246 0.382246 reward 3.18204 time 10000.0 params 331.673 0.407246 0.407246 reward 3.92682 time 10000.0 params 331.673 0.357246 0.357246 reward 5.11576 time 10000.0 params 322.923 0.382246 0.382246 reward 3.62280 time 10000.0 params 357.923 0.382246 0.382246 reward 2.76344 time 10000.0 params 322.923 0.382246 0.382246 reward 2.30346 time 10000.0 params 311.985 0.400996 0.400996 reward 4.12418 time 10000.0 params 322.923 0.382246 0.382246 reward 4.45419 time 10000.0 params 303.235 0.375996 0.375996 reward 5.12455 time 10000.0 params 322.923 0.382246 0.382246 reward 3.83543 time 10000.0 params 324.563 0.399434 0.399434 reward 4.17335 time 10000.0 params 322.923 0.382246 0.382246 reward 3.45640 time 10000.0 params 327.298 0.394746 0.394746 reward 2.73240 time 10000.0 params 322.923 0.382246 0.382246 reward 3.20500 time 10000.0 params 317.454 0.391621 0.391621 reward 4.26858 time 10000.0 params 322.923 0.382246 0.382246 reward 4.86661 time 10000.0 params 332.766 0.385371 0.385371 reward 4.71699 time 10000.0 params 322.923 0.382246 0.382246 reward 4.62019 time 10000.0 params 328.391 0.372871 0.372871 reward 3.78083 time 10000.0 params 322.923 0.382246 0.382246 reward 4.27925 time 10000.0 params 327.571 0.389277 0.389277 reward 1.92124 time 10000.0 params 322.923 0.382246 0.382246 reward 5.11394 time 10000.0 params 328.118 0.37834 0.37834 reward 3.69699 time 10000.0 params 322.923 0.382246 0.382246 reward 4.49859 time 10000.0 params 327.708 0.386543 0.386543 reward 4.17804 time 10000.0 params 322.923 0.382246 0.382246 reward 4.25305 time 10000.0 params 325.247 0.385762 0.385762 reward 4.19558 time 10000.0 params 322.923 0.382246 0.382246 reward 3.42251 time 10000.0 params 327.844 0.383809 0.383809 reward 2.86769 time 10000.0 params 325.247 0.385762 0.385762 reward 3.68459 time 10000.0 params 320.325 0.384199 0.384199 reward 2.99992 time 10000.0 params 325.247 0.385762 0.385762 reward 3.00358 time 10000.0 params 325.965 0.383906 0.383906 reward 4.28064 time 10000.0 params 325.247 0.385762 0.385762 reward 5.15424 time 10000.0 params 322.205 0.384102 0.384102 reward 4.68813 time 10000.0 params 325.247 0.385762 0.385762 reward 4.22667 time 10000.0 params 325.025 0.383955 0.383955 reward 2.28088 time 10000.0 params 325.247 0.385762 0.385762 reward 2.74271 time 10000.0 params 323.145 0.384053 0.384053 reward 3.23739 time 10000.0 params 325.247 0.385762 0.385762 reward 3.87213 time 10000.0 params 324.555 0.383979 0.383979 reward 4.10264 time 10000.0 params 325.247 0.385762 0.385762 reward 4.34951 time 10000.0 params 324.085 0.384004 0.384004 reward 4.84161 time 10000.0 params 325.247 0.385762 0.385762 reward 4.75004 time 10000.0 params 325.136 0.384858 0.384858 reward 4.66863 time 10000.0 params 325.247 0.385762 0.385762 reward 3.98547 time 10000.0 params 326.298 0.386616 0.386616 reward 3.61985 time 10000.0 params 325.247 0.385762 0.385762 reward 4.31640 time 10000.0 params 325.744 0.385963 0.385963 reward 4.06540 time 10000.0 params 325.247 0.385762 0.385762 reward 4.19258 time 10000.0 params 324.638 0.384657 0.384657 reward 3.94398 time 10000.0 params 325.247 0.385762 0.385762 reward 4.63135 time 10000.0 params 324.915 0.384984 0.384984 reward 4.67407 time 10000.0 params 325.247 0.385762 0.385762 reward 3.70494 time 10000.0 params 324.942 0.385209 0.385209 reward 2.30552 time 10000.0 params 325.247 0.385762 0.385762 reward 3.23751 time 10000.0 params 325.191 0.38531 0.38531 reward 4.74526 time 10000.0 params 325.247 0.385762 0.385762 reward 4.33195 time 10000.0 params 325.496 0.385862 0.385862 reward 5.12631 time 10000.0 params 325.247 0.385762 0.385762 reward 4.31633 time 10000.0 params 325.357 0.385699 0.385699 reward 4.31792 time 10000.0 params 325.247 0.385762 0.385762 reward 1.10377 time 10000.0 params 348.474 0.789407 0.789407 reward -0.04690 time 10000.0 params 418.474 0.689407 0.689407 reward -3.00536 time 10000.0 params 418.474 0.789407 0.789407 reward 1.47681 time 10000.0 params 348.474 0.689407 0.689407 reward 1.20480 time 10000.0 params 313.474 0.639407 0.639407 reward 3.07075 time 10000.0 params 278.474 0.789407 0.789407 reward 3.77378 time 10000.0 params 208.474 0.839407 0.839407 reward 4.13689 time 10000.0 params 208.474 0.739407 0.739407 reward 4.06278 time 10000.0 params 138.474 0.714407 0.714407 reward 1.56956 time 10000.0 params 68.4742 0.889407 0.889407 reward 3.83098 time 10000.0 params 138.474 0.839407 0.839407 reward 3.74573 time 10000.0 params 138.474 0.739407 0.739407 reward 1.77975 time 10000.0 params 190.974 0.814407 0.814407 reward 3.39328 time 10000.0 params 208.474 0.789407 0.789407 reward 3.22314 time 10000.0 params 173.474 0.789407 0.789407 reward 0.72043 time 10000.0 params 243.474 0.739407 0.739407 reward 3.53121 time 10000.0 params 190.974 0.776907 0.776907 reward 3.25668 time 10000.0 params 190.974 0.726907 0.726907 reward 2.01713 time 10000.0 params 204.099 0.773782 0.773782 reward 3.78518 time 10000.0 params 208.474 0.764407 0.764407 reward 3.21057 time 10000.0 params 199.724 0.758157 0.758157 reward 3.66480 time 10000.0 params 217.224 0.745657 0.745657 reward 4.33617 time 10000.0 params 212.849 0.748782 0.748782 reward 4.56829 time 10000.0 params 212.849 0.723782 0.723782 reward 4.98143 time 10000.0 params 215.037 0.70347 0.70347 reward 4.04338 time 10000.0 params 219.412 0.712845 0.712845 reward 3.63912 time 10000.0 params 211.209 0.732767 0.732767 reward 4.13719 time 10000.0 params 211.755 0.721438 0.721438 reward 2.75228 time 10000.0 params 213.943 0.726126 0.726126 reward 4.00990 time 10000.0 params 212.849 0.698782 0.698782 reward 3.05111 time 10000.0 params 213.123 0.705618 0.705618 reward 4.55038 time 10000.0 params 213.396 0.712454 0.712454 reward 3.59371 time 10000.0 params 213.943 0.701126 0.701126 reward 3.10553 time 10000.0 params 214.49 0.714798 0.714798 reward 2.06573 time 10000.0 params 214.08 0.704544 0.704544 reward 3.44759 time 10000.0 params 214.216 0.707962 0.707962 reward 3.92500 time 10000.0 params 214.49 0.702298 0.702298 reward 5.47017 time 10000.0 params 215.31 0.697806 0.697806 reward 3.63132 time 10000.0 params 215.857 0.692727 0.692727 reward 4.08250 time 10000.0 params 215.857 0.698977 0.698977 reward 5.01790 time 10000.0 params 215.515 0.699808 0.699808 reward 4.51244 time 10000.0 params 215.789 0.694143 0.694143 reward 3.89179 time 10000.0 params 215.225 0.701138 0.701138 reward 3.87219 time 10000.0 params 215.173 0.700638 0.700638 reward 2.06812 time 10000.0 params 215.413 0.698807 0.698807 reward -1.05568 time 10000.0 params 348.474 0.789407 0.789407 reward 0.68749 time 10000.0 params 348.474 0.789407 0.789407 reward -1.30310 time 10000.0 params 418.474 0.689407 0.689407 reward 1.68540 time 10000.0 params 348.474 0.789407 0.789407 reward 0.57030 time 10000.0 params 418.474 0.789407 0.789407 reward -2.96638 time 10000.0 params 348.474 0.789407 0.789407 reward 1.39183 time 10000.0 params 348.474 0.689407 0.689407 reward -1.72551 time 10000.0 params 348.474 0.789407 0.789407 reward 3.54565 time 10000.0 params 313.474 0.639407 0.639407 reward 3.88941 time 10000.0 params 348.474 0.689407 0.689407 reward 2.42093 time 10000.0 params 278.474 0.789407 0.789407 reward 3.72676 time 10000.0 params 348.474 0.689407 0.689407 reward 3.19546 time 10000.0 params 208.474 0.839407 0.839407 reward 2.03168 time 10000.0 params 278.474 0.789407 0.789407 reward 3.19180 time 10000.0 params 208.474 0.739407 0.739407 reward 0.95798 time 10000.0 params 208.474 0.839407 0.839407 reward 3.64326 time 10000.0 params 138.474 0.714407 0.714407 reward 4.53070 time 10000.0 params 208.474 0.739407 0.739407 reward 1.56074 time 10000.0 params 68.4742 0.889407 0.889407 reward 3.57779 time 10000.0 params 208.474 0.739407 0.739407 reward 4.36617 time 10000.0 params 138.474 0.839407 0.839407 reward 4.59929 time 10000.0 params 208.474 0.739407 0.739407 reward 3.85719 time 10000.0 params 138.474 0.739407 0.739407 reward 3.61283 time 10000.0 params 208.474 0.739407 0.739407 reward 2.51654 time 10000.0 params 190.974 0.814407 0.814407 reward 4.76468 time 10000.0 params 208.474 0.739407 0.739407 reward 1.94195 time 10000.0 params 208.474 0.789407 0.789407 reward 3.06042 time 10000.0 params 208.474 0.739407 0.739407 reward 3.21617 time 10000.0 params 173.474 0.789407 0.789407 reward 5.13573 time 10000.0 params 208.474 0.739407 0.739407 reward 4.52727 time 10000.0 params 243.474 0.739407 0.739407 reward 3.12029 time 10000.0 params 208.474 0.739407 0.739407 reward 1.68610 time 10000.0 params 190.974 0.776907 0.776907 reward 3.52850 time 10000.0 params 208.474 0.739407 0.739407 reward 4.12603 time 10000.0 params 190.974 0.726907 0.726907 reward 4.68136 time 10000.0 params 208.474 0.739407 0.739407 reward 3.79657 time 10000.0 params 204.099 0.773782 0.773782 reward 3.74595 time 10000.0 params 208.474 0.739407 0.739407 reward 4.24612 time 10000.0 params 208.474 0.764407 0.764407 reward 4.50083 time 10000.0 params 208.474 0.739407 0.739407 reward 3.62631 time 10000.0 params 199.724 0.758157 0.758157 reward 4.60921 time 10000.0 params 208.474 0.739407 0.739407 reward 3.82238 time 10000.0 params 217.224 0.745657 0.745657 reward 4.04398 time 10000.0 params 208.474 0.739407 0.739407 reward 2.26961 time 10000.0 params 212.849 0.748782 0.748782 reward 2.67948 time 10000.0 params 208.474 0.739407 0.739407 reward 5.12950 time 10000.0 params 212.849 0.723782 0.723782 reward 5.47821 time 10000.0 params 212.849 0.748782 0.748782 reward 3.67040 time 10000.0 params 215.037 0.70347 0.70347 reward 4.67876 time 10000.0 params 212.849 0.723782 0.723782 reward 3.17780 time 10000.0 params 219.412 0.712845 0.712845 reward 5.09444 time 10000.0 params 215.037 0.70347 0.70347 reward 4.94059 time 10000.0 params 211.209 0.732767 0.732767 reward 5.53032 time 10000.0 params 215.037 0.70347 0.70347 reward 2.59467 time 10000.0 params 211.755 0.721438 0.721438 reward 3.44153 time 10000.0 params 215.037 0.70347 0.70347 reward 3.24402 time 10000.0 params 213.943 0.726126 0.726126 reward 5.04585 time 10000.0 params 215.037 0.70347 0.70347 reward 4.59148 time 10000.0 params 212.849 0.698782 0.698782 reward 4.67792 time 10000.0 params 215.037 0.70347 0.70347 reward 4.97971 time 10000.0 params 213.123 0.705618 0.705618 reward 3.03615 time 10000.0 params 215.037 0.70347 0.70347 reward 4.49516 time 10000.0 params 213.396 0.712454 0.712454 reward 4.95789 time 10000.0 params 215.037 0.70347 0.70347 reward 5.44934 time 10000.0 params 213.943 0.701126 0.701126 reward 2.95489 time 10000.0 params 215.037 0.70347 0.70347 reward 4.12399 time 10000.0 params 214.49 0.714798 0.714798 reward 5.15537 time 10000.0 params 215.037 0.70347 0.70347 reward 3.65329 time 10000.0 params 214.08 0.704544 0.704544 reward 2.68956 time 10000.0 params 215.037 0.70347 0.70347 reward 2.86169 time 10000.0 params 214.216 0.707962 0.707962 reward 3.32076 time 10000.0 params 215.037 0.70347 0.70347 reward 3.36881 time 10000.0 params 214.49 0.702298 0.702298 reward 4.47992 time 10000.0 params 215.037 0.70347 0.70347 reward 3.55480 time 10000.0 params 215.31 0.697806 0.697806 reward 2.65829 time 10000.0 params 215.037 0.70347 0.70347 reward 2.61470 time 10000.0 params 215.857 0.692727 0.692727 reward 4.59380 time 10000.0 params 215.31 0.697806 0.697806 reward 2.56202 time 10000.0 params 215.857 0.698977 0.698977 reward 3.57735 time 10000.0 params 215.31 0.697806 0.697806 reward 3.51407 time 10000.0 params 366.58 0.386808 0.386808 reward 4.25917 time 10000.0 params 296.58 0.486808 0.486808 reward 4.37202 time 10000.0 params 296.58 0.386808 0.386808 reward 3.58310 time 10000.0 params 226.58 0.486808 0.486808 reward 2.70943 time 10000.0 params 261.58 0.461808 0.461808 reward 3.95077 time 10000.0 params 261.58 0.436808 0.436808 reward 3.03688 time 10000.0 params 296.58 0.436808 0.436808 reward 4.23505 time 10000.0 params 261.58 0.386808 0.386808 reward 3.85969 time 10000.0 params 296.58 0.336808 0.336808 reward 4.31275 time 10000.0 params 270.33 0.411808 0.411808 reward 4.61726 time 10000.0 params 305.33 0.411808 0.411808 reward 2.02463 time 10000.0 params 327.205 0.424308 0.424308 reward 2.82048 time 10000.0 params 331.58 0.386808 0.386808 reward 4.75781 time 10000.0 params 285.643 0.405558 0.405558 reward 4.81518 time 10000.0 params 294.393 0.430558 0.430558 reward 4.97550 time 10000.0 params 293.299 0.452433 0.452433 reward 3.65073 time 10000.0 params 273.611 0.446183 0.446183 reward 4.20035 time 10000.0 params 297.401 0.420402 0.420402 reward 3.37749 time 10000.0 params 289.471 0.428995 0.428995 reward 3.83576 time 10000.0 params 299.315 0.43212 0.43212 reward 2.89864 time 10000.0 params 303.143 0.455558 0.455558 reward 2.52803 time 10000.0 params 292.889 0.435636 0.435636 reward 3.05150 time 10000.0 params 291.385 0.440714 0.440714 reward 3.38449 time 10000.0 params 296.307 0.442277 0.442277 reward 2.63089 time 10000.0 params 298.221 0.453995 0.453995 reward 3.01508 time 10000.0 params 293.094 0.444034 0.444034 reward 3.93767 time 10000.0 params 292.342 0.446573 0.446573 reward 2.69827 time 10000.0 params 294.803 0.447355 0.447355 reward 3.13068 time 10000.0 params 290.838 0.451652 0.451652 reward 3.44400 time 10000.0 params 291.829 0.450577 0.450577 reward 3.94000 time 10000.0 params 293.812 0.448429 0.448429 reward 4.16734 time 10000.0 params 294.769 0.454288 0.454288 reward 3.69489 time 10000.0 params 294.256 0.458292 0.458292 reward 3.53017 time 10000.0 params 293.923 0.450895 0.450895 reward 5.15187 time 10000.0 params 294.034 0.453361 0.453361 reward 3.00056 time 10000.0 params 293.555 0.450431 0.450431 reward 3.63167 time 10000.0 params 293.777 0.455363 0.455363 reward 4.10861 time 10000.0 params 293.722 0.45413 0.45413 reward 2.19983 time 10000.0 params 293.611 0.451664 0.451664 reward 2.21844 time 10000.0 params 293.694 0.453513 0.453513 reward 5.44403 time 10000.0 params 293.878 0.453745 0.453745 reward 4.07660 time 10000.0 params 293.666 0.452897 0.452897 reward 3.13506 time 10000.0 params 294.245 0.454209 0.454209 reward 3.55542 time 10000.0 params 293.811 0.453225 0.453225 reward 3.11512 time 10000.0 params 293.956 0.453553 0.453553 reward 4.21919 time 10000.0 params 293.772 0.453321 0.453321 reward 3.88656 time 10000.0 params 366.58 0.386808 0.386808 reward 4.37660 time 10000.0 params 366.58 0.386808 0.386808 reward 3.49779 time 10000.0 params 296.58 0.486808 0.486808 reward 3.37501 time 10000.0 params 366.58 0.386808 0.386808 reward 2.87987 time 10000.0 params 296.58 0.386808 0.386808 reward 4.85424 time 10000.0 params 296.58 0.486808 0.486808 reward 4.09888 time 10000.0 params 226.58 0.486808 0.486808 reward 3.89361 time 10000.0 params 296.58 0.386808 0.386808 reward 4.58659 time 10000.0 params 261.58 0.461808 0.461808 reward 3.50698 time 10000.0 params 296.58 0.386808 0.386808 reward 3.94896 time 10000.0 params 261.58 0.436808 0.436808 reward 4.92802 time 10000.0 params 296.58 0.386808 0.386808 reward 3.06425 time 10000.0 params 296.58 0.436808 0.436808 reward 3.43963 time 10000.0 params 296.58 0.386808 0.386808 reward 3.82913 time 10000.0 params 261.58 0.386808 0.386808 reward 3.79550 time 10000.0 params 296.58 0.386808 0.386808 reward 3.31589 time 10000.0 params 296.58 0.336808 0.336808 reward 3.80294 time 10000.0 params 296.58 0.386808 0.386808 reward 3.79526 time 10000.0 params 270.33 0.411808 0.411808 reward 3.91700 time 10000.0 params 296.58 0.386808 0.386808 reward 2.93237 time 10000.0 params 305.33 0.411808 0.411808 reward 2.42675 time 10000.0 params 296.58 0.386808 0.386808 reward 2.22700 time 10000.0 params 327.205 0.424308 0.424308 reward 3.33289 time 10000.0 params 305.33 0.411808 0.411808 reward 3.75336 time 10000.0 params 331.58 0.386808 0.386808 reward 4.68434 time 10000.0 params 305.33 0.411808 0.411808 reward 3.46276 time 10000.0 params 285.643 0.405558 0.405558 reward 3.83786 time 10000.0 params 305.33 0.411808 0.411808 reward 3.87016 time 10000.0 params 294.393 0.430558 0.430558 reward 4.22839 time 10000.0 params 285.643 0.405558 0.405558 reward 3.99389 time 10000.0 params 293.299 0.452433 0.452433 reward 2.84933 time 10000.0 params 294.393 0.430558 0.430558 reward 4.14698 time 10000.0 params 273.611 0.446183 0.446183 reward 3.09048 time 10000.0 params 293.299 0.452433 0.452433 reward 3.70469 time 10000.0 params 297.401 0.420402 0.420402 reward 5.09539 time 10000.0 params 293.299 0.452433 0.452433 reward 4.17972 time 10000.0 params 289.471 0.428995 0.428995 reward 1.88340 time 10000.0 params 293.299 0.452433 0.452433 reward 3.85601 time 10000.0 params 299.315 0.43212 0.43212 reward 4.55337 time 10000.0 params 293.299 0.452433 0.452433 reward 4.56018 time 10000.0 params 303.143 0.455558 0.455558 reward 2.84785 time 10000.0 params 293.299 0.452433 0.452433 reward 3.71093 time 10000.0 params 292.889 0.435636 0.435636 reward 2.64414 time 10000.0 params 293.299 0.452433 0.452433 reward 2.48463 time 10000.0 params 291.385 0.440714 0.440714 reward 3.96358 time 10000.0 params 293.299 0.452433 0.452433 reward 4.52279 time 10000.0 params 296.307 0.442277 0.442277 reward 4.18508 time 10000.0 params 293.299 0.452433 0.452433 reward 4.08318 time 10000.0 params 298.221 0.453995 0.453995 reward 4.47319 time 10000.0 params 293.299 0.452433 0.452433 reward 4.00473 time 10000.0 params 293.094 0.444034 0.444034 reward 2.14696 time 10000.0 params 293.299 0.452433 0.452433 reward 4.31618 time 10000.0 params 292.342 0.446573 0.446573 reward 2.21585 time 10000.0 params 293.299 0.452433 0.452433 reward 5.06995 time 10000.0 params 294.803 0.447355 0.447355 reward 2.44694 time 10000.0 params 293.299 0.452433 0.452433 reward 4.45167 time 10000.0 params 290.838 0.451652 0.451652 reward 3.90128 time 10000.0 params 293.299 0.452433 0.452433 reward 4.54930 time 10000.0 params 291.829 0.450577 0.450577 reward 3.91013 time 10000.0 params 293.299 0.452433 0.452433 reward 1.96688 time 10000.0 params 293.812 0.448429 0.448429 reward 3.57789 time 10000.0 params 293.299 0.452433 0.452433 reward 4.59414 time 10000.0 params 294.769 0.454288 0.454288 reward 4.93643 time 10000.0 params 293.299 0.452433 0.452433 reward 4.06399 time 10000.0 params 294.256 0.458292 0.458292 reward 4.92335 time 10000.0 params 293.299 0.452433 0.452433 reward 2.53964 time 10000.0 params 293.923 0.450895 0.450895 reward 3.96932 time 10000.0 params 293.299 0.452433 0.452433 reward 4.39707 time 10000.0 params 294.034 0.453361 0.453361 reward 1.59497 time 10000.0 params 293.299 0.452433 0.452433 reward 3.65657 time 10000.0 params 293.555 0.450431 0.450431 reward 2.55320 time 10000.0 params 294.034 0.453361 0.453361 reward 3.51335 time 10000.0 params 293.777 0.455363 0.455363 reward 3.83558 time 10000.0 params 294.034 0.453361 0.453361 reward 3.05082 time 10000.0 params 293.722 0.45413 0.45413 reward 3.57284 time 10000.0 params 294.034 0.453361 0.453361 reward 3.44988 time 10000.0 params 293.611 0.451664 0.451664 reward 2.45256 time 10000.0 params 294.034 0.453361 0.453361 reward 4.63179 time 10000.0 params 293.694 0.453513 0.453513 reward 4.50194 time 10000.0 params 294.034 0.453361 0.453361 reward 1.54489 time 10000.0 params 406.337 0.417522 0.417522 reward 0.77772 time 10000.0 params 476.337 0.517522 0.517522 reward 1.25567 time 10000.0 params 476.337 0.417522 0.417522 reward 4.47452 time 10000.0 params 406.337 0.317522 0.317522 reward 2.38044 time 10000.0 params 371.337 0.217522 0.217522 reward 4.09541 time 10000.0 params 336.337 0.317522 0.317522 reward 2.35725 time 10000.0 params 336.337 0.217522 0.217522 reward 3.36939 time 10000.0 params 353.837 0.267522 0.267522 reward 3.95342 time 10000.0 params 388.837 0.367522 0.367522 reward 4.00029 time 10000.0 params 380.087 0.342522 0.342522 reward 4.07520 time 10000.0 params 362.587 0.292522 0.292522 reward 3.19911 time 10000.0 params 366.962 0.305022 0.305022 reward 3.15502 time 10000.0 params 384.462 0.305022 0.305022 reward 3.61930 time 10000.0 params 371.337 0.317522 0.317522 reward 4.31440 time 10000.0 params 393.212 0.330022 0.330022 reward 3.72597 time 10000.0 params 428.212 0.330022 0.330022 reward 4.01582 time 10000.0 params 413.993 0.326897 0.326897 reward 4.20272 time 10000.0 params 385.556 0.320647 0.320647 reward 5.24009 time 10000.0 params 392.665 0.32221 0.32221 reward 4.15535 time 10000.0 params 405.79 0.30971 0.30971 reward 4.92024 time 10000.0 params 396.357 0.324944 0.324944 reward 3.26907 time 10000.0 params 382.685 0.329632 0.329632 reward 3.89228 time 10000.0 params 400.424 0.32055 0.32055 reward 4.03626 time 10000.0 params 394.511 0.323577 0.323577 reward 4.75819 time 10000.0 params 399.501 0.319866 0.319866 reward 3.28504 time 10000.0 params 397.655 0.318499 0.318499 reward 4.79465 time 10000.0 params 395.297 0.322307 0.322307 reward 3.28449 time 10000.0 params 388.461 0.324651 0.324651 reward 4.27466 time 10000.0 params 396.741 0.321062 0.321062 reward 3.27762 time 10000.0 params 393.981 0.322259 0.322259 reward 3.00972 time 10000.0 params 396.083 0.321038 0.321038 reward 4.26836 time 10000.0 params 390.563 0.323431 0.323431 reward 5.33852 time 10000.0 params 389.247 0.323382 0.323382 reward 3.73500 time 10000.0 params 386.88 0.323943 0.323943 reward 3.79490 time 10000.0 params 391.349 0.322161 0.322161 reward 3.87409 time 10000.0 params 390.76 0.323113 0.323113 reward 4.81124 time 10000.0 params 389.905 0.323406 0.323406 reward 3.44776 time 10000.0 params 390.956 0.322796 0.322796 reward 3.29609 time 10000.0 params 388.196 0.323992 0.323992 reward 4.68400 time 10000.0 params 390.266 0.323095 0.323095 reward 4.66837 time 10000.0 params 388.886 0.323693 0.323693 reward 3.39758 time 10000.0 params 389.921 0.323244 0.323244 reward 2.98182 time 10000.0 params 389.576 0.323394 0.323394 reward 2.84334 time 10000.0 params 389.757 0.323238 0.323238 reward 4.45642 time 10000.0 params 406.337 0.417522 0.417522 reward 4.05286 time 10000.0 params 406.337 0.417522 0.417522 reward -0.52819 time 10000.0 params 476.337 0.517522 0.517522 reward 0.88482 time 10000.0 params 406.337 0.417522 0.417522 reward -0.17817 time 10000.0 params 476.337 0.417522 0.417522 reward 4.55316 time 10000.0 params 406.337 0.417522 0.417522 reward 3.91431 time 10000.0 params 406.337 0.317522 0.317522 reward 2.94774 time 10000.0 params 406.337 0.417522 0.417522 reward 2.31071 time 10000.0 params 371.337 0.217522 0.217522 reward 3.80468 time 10000.0 params 406.337 0.317522 0.317522 reward 4.23496 time 10000.0 params 336.337 0.317522 0.317522 reward 4.47389 time 10000.0 params 406.337 0.317522 0.317522 reward 2.79390 time 10000.0 params 336.337 0.217522 0.217522 reward 3.93565 time 10000.0 params 406.337 0.317522 0.317522 reward 3.84092 time 10000.0 params 353.837 0.267522 0.267522 reward 3.38058 time 10000.0 params 406.337 0.317522 0.317522 reward 4.25813 time 10000.0 params 388.837 0.367522 0.367522 reward 2.88109 time 10000.0 params 406.337 0.317522 0.317522 reward 3.50190 time 10000.0 params 380.087 0.342522 0.342522 reward 4.44115 time 10000.0 params 406.337 0.317522 0.317522 reward 4.43934 time 10000.0 params 362.587 0.292522 0.292522 reward 4.35033 time 10000.0 params 406.337 0.317522 0.317522 reward 3.72660 time 10000.0 params 366.962 0.305022 0.305022 reward 3.94280 time 10000.0 params 406.337 0.317522 0.317522 reward 3.99991 time 10000.0 params 384.462 0.305022 0.305022 reward 3.84473 time 10000.0 params 406.337 0.317522 0.317522 reward 4.04838 time 10000.0 params 371.337 0.317522 0.317522 reward 3.06019 time 10000.0 params 406.337 0.317522 0.317522 reward 4.90229 time 10000.0 params 393.212 0.330022 0.330022 reward 3.79471 time 10000.0 params 406.337 0.317522 0.317522 reward 3.84389 time 10000.0 params 428.212 0.330022 0.330022 reward 3.48643 time 10000.0 params 406.337 0.317522 0.317522 reward 2.17375 time 10000.0 params 413.993 0.326897 0.326897 reward 2.86842 time 10000.0 params 406.337 0.317522 0.317522 reward 3.75131 time 10000.0 params 385.556 0.320647 0.320647 reward 3.96439 time 10000.0 params 406.337 0.317522 0.317522 reward 3.93601 time 10000.0 params 392.665 0.32221 0.32221 reward 3.49969 time 10000.0 params 406.337 0.317522 0.317522 reward 2.73716 time 10000.0 params 405.79 0.30971 0.30971 reward 2.53630 time 10000.0 params 392.665 0.32221 0.32221 reward 3.40442 time 10000.0 params 396.357 0.324944 0.324944 reward 4.33906 time 10000.0 params 392.665 0.32221 0.32221 reward 2.85036 time 10000.0 params 382.685 0.329632 0.329632 reward 2.94353 time 10000.0 params 392.665 0.32221 0.32221 reward 4.29430 time 10000.0 params 400.424 0.32055 0.32055 reward 2.84140 time 10000.0 params 392.665 0.32221 0.32221 reward 4.69880 time 10000.0 params 394.511 0.323577 0.323577 reward 3.31131 time 10000.0 params 392.665 0.32221 0.32221 reward 2.87279 time 10000.0 params 399.501 0.319866 0.319866 reward 3.81922 time 10000.0 params 392.665 0.32221 0.32221 reward 3.76965 time 10000.0 params 397.655 0.318499 0.318499 reward 2.93622 time 10000.0 params 392.665 0.32221 0.32221 reward 4.83288 time 10000.0 params 395.297 0.322307 0.322307 reward 3.32438 time 10000.0 params 392.665 0.32221 0.32221 reward 3.80433 time 10000.0 params 388.461 0.324651 0.324651 reward 3.37359 time 10000.0 params 392.665 0.32221 0.32221 reward 4.40589 time 10000.0 params 396.741 0.321062 0.321062 reward 4.81453 time 10000.0 params 392.665 0.32221 0.32221 reward 3.53586 time 10000.0 params 393.981 0.322259 0.322259 reward 5.12847 time 10000.0 params 392.665 0.32221 0.32221 reward 1.99545 time 10000.0 params 396.083 0.321038 0.321038 reward 3.37734 time 10000.0 params 392.665 0.32221 0.32221 reward 4.27399 time 10000.0 params 390.563 0.323431 0.323431 reward 3.79306 time 10000.0 params 392.665 0.32221 0.32221 reward 4.17518 time 10000.0 params 389.247 0.323382 0.323382 reward 3.79297 time 10000.0 params 392.665 0.32221 0.32221 reward 4.28904 time 10000.0 params 386.88 0.323943 0.323943 reward 1.55235 time 10000.0 params 389.247 0.323382 0.323382 reward 3.89094 time 10000.0 params 391.349 0.322161 0.322161 reward 4.24059 time 10000.0 params 389.247 0.323382 0.323382 reward 3.89827 time 10000.0 params 390.76 0.323113 0.323113 reward 3.57352 time 10000.0 params 389.247 0.323382 0.323382 reward 2.79978 time 10000.0 params 389.905 0.323406 0.323406 reward 3.95530 time 10000.0 params 389.247 0.323382 0.323382 reward 4.35891 time 10000.0 params 390.956 0.322796 0.322796 reward 4.26515 time 10000.0 params 389.247 0.323382 0.323382 reward 3.72170 time 10000.0 params 388.196 0.323992 0.323992 reward 4.27061 time 10000.0 params 389.247 0.323382 0.323382 reward 3.44768 time 10000.0 params 390.266 0.323095 0.323095 reward 4.71740 time 10000.0 params 389.247 0.323382 0.323382 reward 4.00476 time 10000.0 params 279.209 0.384159 0.384159 reward 3.27223 time 10000.0 params 209.209 0.484159 0.484159 reward 2.71302 time 10000.0 params 209.209 0.384159 0.384159 reward 4.17801 time 10000.0 params 279.209 0.484159 0.484159 reward 3.01048 time 10000.0 params 314.209 0.534159 0.534159 reward 3.68302 time 10000.0 params 349.209 0.384159 0.384159 reward 1.11901 time 10000.0 params 314.209 0.409159 0.409159 reward 3.19133 time 10000.0 params 279.209 0.434159 0.434159 reward 4.51407 time 10000.0 params 314.209 0.434159 0.434159 reward 4.58209 time 10000.0 params 314.209 0.484159 0.484159 reward 4.04959 time 10000.0 params 331.709 0.509159 0.509159 reward 5.30997 time 10000.0 params 349.209 0.434159 0.434159 reward 4.64350 time 10000.0 params 384.209 0.409159 0.409159 reward 2.62850 time 10000.0 params 349.209 0.484159 0.484159 reward 2.50561 time 10000.0 params 322.959 0.446659 0.446659 reward 3.10999 time 10000.0 params 331.709 0.459159 0.459159 reward 3.98546 time 10000.0 params 331.709 0.434159 0.434159 reward 3.71444 time 10000.0 params 349.209 0.409159 0.409159 reward 3.52669 time 10000.0 params 344.834 0.421659 0.421659 reward 3.50524 time 10000.0 params 349.209 0.421659 0.421659 reward 1.60949 time 10000.0 params 340.459 0.434159 0.434159 reward 3.53029 time 10000.0 params 357.959 0.421659 0.421659 reward 5.18978 time 10000.0 params 357.959 0.434159 0.434159 reward 4.43309 time 10000.0 params 349.209 0.446659 0.446659 reward 3.31629 time 10000.0 params 351.396 0.440409 0.440409 reward 5.41784 time 10000.0 params 353.584 0.434159 0.434159 reward 4.08409 time 10000.0 params 349.209 0.440409 0.440409 reward 4.54515 time 10000.0 params 353.584 0.427909 0.427909 reward 1.82975 time 10000.0 params 352.49 0.431034 0.431034 reward 2.11095 time 10000.0 params 353.584 0.431034 0.431034 reward 4.03369 time 10000.0 params 351.396 0.434159 0.434159 reward 3.10498 time 10000.0 params 351.396 0.437284 0.437284 reward 4.08756 time 10000.0 params 351.943 0.435721 0.435721 reward 3.76545 time 10000.0 params 354.131 0.435721 0.435721 reward 4.15168 time 10000.0 params 352.08 0.43455 0.43455 reward 3.59778 time 10000.0 params 353.72 0.432987 0.432987 reward 5.41229 time 10000.0 params 352.387 0.435038 0.435038 reward 4.68451 time 10000.0 params 353.891 0.434647 0.434647 reward 3.76124 time 10000.0 params 353.438 0.434623 0.434623 reward 3.66173 time 10000.0 params 352.986 0.434598 0.434598 reward 3.02547 time 10000.0 params 353.737 0.434403 0.434403 reward 4.60461 time 10000.0 params 352.832 0.434354 0.434354 reward 2.24643 time 10000.0 params 353.43 0.433915 0.433915 reward 5.08579 time 10000.0 params 353.097 0.434427 0.434427 reward 2.56079 time 10000.0 params 279.209 0.384159 0.384159 reward 3.70378 time 10000.0 params 279.209 0.384159 0.384159 reward 4.24949 time 10000.0 params 209.209 0.484159 0.484159 reward 3.56575 time 10000.0 params 279.209 0.384159 0.384159 reward 2.64583 time 10000.0 params 209.209 0.384159 0.384159 reward 4.39817 time 10000.0 params 279.209 0.384159 0.384159 reward 4.58923 time 10000.0 params 279.209 0.484159 0.484159 reward 3.60956 time 10000.0 params 279.209 0.384159 0.384159 reward 2.42838 time 10000.0 params 314.209 0.534159 0.534159 reward 4.67063 time 10000.0 params 279.209 0.484159 0.484159 reward 4.96389 time 10000.0 params 349.209 0.384159 0.384159 reward 3.73676 time 10000.0 params 279.209 0.484159 0.484159 reward 4.85929 time 10000.0 params 314.209 0.409159 0.409159 reward 4.58634 time 10000.0 params 279.209 0.484159 0.484159 reward 4.17315 time 10000.0 params 279.209 0.434159 0.434159 reward 2.56121 time 10000.0 params 279.209 0.484159 0.484159 reward 3.61900 time 10000.0 params 314.209 0.434159 0.434159 reward 3.60211 time 10000.0 params 279.209 0.484159 0.484159 reward 3.66459 time 10000.0 params 314.209 0.484159 0.484159 reward 4.50514 time 10000.0 params 314.209 0.434159 0.434159 reward 3.46539 time 10000.0 params 331.709 0.509159 0.509159 reward 3.42579 time 10000.0 params 314.209 0.484159 0.484159 reward 5.06274 time 10000.0 params 349.209 0.434159 0.434159 reward 2.57829 time 10000.0 params 314.209 0.484159 0.484159 reward 1.96315 time 10000.0 params 384.209 0.409159 0.409159 reward 3.23612 time 10000.0 params 349.209 0.434159 0.434159 reward 2.47716 time 10000.0 params 349.209 0.484159 0.484159 reward 3.90106 time 10000.0 params 349.209 0.434159 0.434159 reward 4.38358 time 10000.0 params 322.959 0.446659 0.446659 reward 3.98715 time 10000.0 params 349.209 0.434159 0.434159 reward 4.57617 time 10000.0 params 331.709 0.459159 0.459159 reward 3.65798 time 10000.0 params 349.209 0.434159 0.434159 reward 4.29481 time 10000.0 params 331.709 0.434159 0.434159 reward 2.67614 time 10000.0 params 349.209 0.434159 0.434159 reward 3.83628 time 10000.0 params 349.209 0.409159 0.409159 reward 3.97540 time 10000.0 params 349.209 0.434159 0.434159 reward 4.42894 time 10000.0 params 344.834 0.421659 0.421659 reward 3.55918 time 10000.0 params 349.209 0.434159 0.434159 reward 4.94681 time 10000.0 params 349.209 0.421659 0.421659 reward 3.99661 time 10000.0 params 349.209 0.434159 0.434159 reward 4.88857 time 10000.0 params 340.459 0.434159 0.434159 reward 6.10901 time 10000.0 params 349.209 0.434159 0.434159 reward 5.13053 time 10000.0 params 357.959 0.421659 0.421659 reward 2.13528 time 10000.0 params 349.209 0.434159 0.434159 reward 2.42216 time 10000.0 params 357.959 0.434159 0.434159 reward 2.83126 time 10000.0 params 349.209 0.434159 0.434159 reward 4.21509 time 10000.0 params 349.209 0.446659 0.446659 reward 2.25889 time 10000.0 params 349.209 0.434159 0.434159 reward 4.00361 time 10000.0 params 351.396 0.440409 0.440409 reward 2.57594 time 10000.0 params 349.209 0.434159 0.434159 reward 4.77709 time 10000.0 params 353.584 0.434159 0.434159 reward 4.57130 time 10000.0 params 349.209 0.434159 0.434159 reward 4.22729 time 10000.0 params 349.209 0.440409 0.440409 reward 2.29062 time 10000.0 params 353.584 0.434159 0.434159 reward 4.52106 time 10000.0 params 353.584 0.427909 0.427909 reward 2.61679 time 10000.0 params 353.584 0.434159 0.434159 reward 1.72737 time 10000.0 params 352.49 0.431034 0.431034 reward 4.61007 time 10000.0 params 353.584 0.434159 0.434159 reward 3.24709 time 10000.0 params 353.584 0.431034 0.431034 reward 4.65589 time 10000.0 params 353.584 0.434159 0.434159 reward 4.60810 time 10000.0 params 351.396 0.434159 0.434159 reward 5.67167 time 10000.0 params 353.584 0.434159 0.434159 reward 2.64038 time 10000.0 params 351.396 0.437284 0.437284 reward 5.20892 time 10000.0 params 353.584 0.434159 0.434159 reward 3.12893 time 10000.0 params 351.943 0.435721 0.435721 reward 3.10161 time 10000.0 params 353.584 0.434159 0.434159 reward 1.59684 time 10000.0 params 354.131 0.435721 0.435721 reward 2.48539 time 10000.0 params 353.584 0.434159 0.434159 reward 3.51855 time 10000.0 params 352.08 0.43455 0.43455 reward 5.24720 time 10000.0 params 353.584 0.434159 0.434159 reward 4.57506 time 10000.0 params 353.72 0.432987 0.432987 reward 4.76556 time 10000.0 params 353.584 0.434159 0.434159 reward 2.44646 time 10000.0 params 352.387 0.435038 0.435038 reward 4.12190 time 10000.0 params 353.584 0.434159 0.434159 reward 4.47879 time 10000.0 params 353.891 0.434647 0.434647 reward 3.25298 time 10000.0 params 353.584 0.434159 0.434159 reward 4.68925 time 10000.0 params 353.438 0.434623 0.434623 reward 2.90487 time 10000.0 params 353.584 0.434159 0.434159 reward 3.59350 time 10000.0 params 352.986 0.434598 0.434598 reward 3.97419 time 10000.0 params 353.584 0.434159 0.434159 reward 2.31524 time 10000.0 params 290.205 0.760095 0.760095 reward 3.43147 time 10000.0 params 220.205 0.660095 0.660095 reward 3.03353 time 10000.0 params 220.205 0.760095 0.760095 reward 3.35542 time 10000.0 params 150.205 0.660095 0.660095 reward 3.33596 time 10000.0 params 150.205 0.560095 0.560095 reward 3.93640 time 10000.0 params 167.705 0.610095 0.610095 reward 4.79479 time 10000.0 params 237.705 0.610095 0.610095 reward 3.48978 time 10000.0 params 281.455 0.585095 0.585095 reward 3.98357 time 10000.0 params 185.205 0.560095 0.560095 reward 3.93684 time 10000.0 params 255.205 0.560095 0.560095 reward 2.67055 time 10000.0 params 233.33 0.572595 0.572595 reward 4.20855 time 10000.0 params 211.455 0.585095 0.585095 reward 4.77390 time 10000.0 params 246.455 0.585095 0.585095 reward 1.12094 time 10000.0 params 272.705 0.610095 0.610095 reward 4.60299 time 10000.0 params 226.768 0.591345 0.591345 reward 4.69123 time 10000.0 params 257.393 0.603845 0.603845 reward 2.97784 time 10000.0 params 249.737 0.60072 0.60072 reward 5.12036 time 10000.0 params 247.549 0.60697 0.60697 reward 3.00371 time 10000.0 params 242.08 0.597595 0.597595 reward 5.00261 time 10000.0 params 243.174 0.61947 0.61947 reward 5.66149 time 10000.0 params 253.018 0.616345 0.616345 reward 3.89428 time 10000.0 params 260.674 0.61947 0.61947 reward 4.57038 time 10000.0 params 257.393 0.603845 0.603845 reward 2.72991 time 10000.0 params 246.729 0.615564 0.615564 reward 6.14147 time 10000.0 params 250.284 0.611658 0.611658 reward 4.67516 time 10000.0 params 248.096 0.617908 0.617908 reward 3.38645 time 10000.0 params 255.205 0.610095 0.610095 reward 3.14168 time 10000.0 params 249.873 0.615955 0.615955 reward 3.62196 time 10000.0 params 251.651 0.614002 0.614002 reward 2.27630 time 10000.0 params 249.19 0.614783 0.614783 reward 4.28337 time 10000.0 params 252.744 0.610877 0.610877 reward 3.57814 time 10000.0 params 251.377 0.608533 0.608533 reward 3.10559 time 10000.0 params 251.582 0.612635 0.612635 reward 2.72359 time 10000.0 params 250.967 0.61283 0.61283 reward 3.66298 time 10000.0 params 251.514 0.611267 0.611267 reward 3.16183 time 10000.0 params 250.83 0.610095 0.610095 reward 3.09046 time 10000.0 params 250.865 0.610779 0.610779 reward 4.45807 time 10000.0 params 250.557 0.610877 0.610877 reward 4.17540 time 10000.0 params 250.899 0.611463 0.611463 reward 4.12763 time 10000.0 params 249.942 0.611072 0.611072 reward 3.44770 time 10000.0 params 250.66 0.611365 0.611365 reward 4.65517 time 10000.0 params 250.42 0.611267 0.611267 reward 4.02171 time 10000.0 params 250.591 0.61156 0.61156 reward 4.61200 time 10000.0 params 250.113 0.611365 0.611365 reward 3.65760 time 10000.0 params 250.232 0.611414 0.611414 reward 4.40504 time 10000.0 params 250.352 0.611463 0.611463 reward 4.50910 time 10000.0 params 250.198 0.611512 0.611512 reward 4.21184 time 10000.0 params 290.205 0.760095 0.760095 reward 3.54020 time 10000.0 params 290.205 0.760095 0.760095 reward 3.79408 time 10000.0 params 220.205 0.660095 0.660095 reward 1.81483 time 10000.0 params 290.205 0.760095 0.760095 reward 3.02810 time 10000.0 params 220.205 0.760095 0.760095 reward 2.96882 time 10000.0 params 220.205 0.660095 0.660095 reward 3.60730 time 10000.0 params 150.205 0.660095 0.660095 reward 2.99363 time 10000.0 params 220.205 0.660095 0.660095 reward 2.43449 time 10000.0 params 150.205 0.560095 0.560095 reward 4.44319 time 10000.0 params 220.205 0.660095 0.660095 reward 3.72533 time 10000.0 params 167.705 0.610095 0.610095 reward 3.02770 time 10000.0 params 220.205 0.660095 0.660095 reward 3.45234 time 10000.0 params 237.705 0.610095 0.610095 reward 3.36443 time 10000.0 params 167.705 0.610095 0.610095 reward 4.38848 time 10000.0 params 281.455 0.585095 0.585095 reward 2.32669 time 10000.0 params 237.705 0.610095 0.610095 reward 4.02718 time 10000.0 params 185.205 0.560095 0.560095 reward 4.78919 time 10000.0 params 237.705 0.610095 0.610095 reward 4.76228 time 10000.0 params 255.205 0.560095 0.560095 reward 3.41167 time 10000.0 params 237.705 0.610095 0.610095 reward 4.53331 time 10000.0 params 233.33 0.572595 0.572595 reward 3.84906 time 10000.0 params 237.705 0.610095 0.610095 reward 3.35507 time 10000.0 params 211.455 0.585095 0.585095 reward 2.69227 time 10000.0 params 237.705 0.610095 0.610095 reward 1.52649 time 10000.0 params 246.455 0.585095 0.585095 reward 3.67961 time 10000.0 params 237.705 0.610095 0.610095 reward 2.99470 time 10000.0 params 272.705 0.610095 0.610095 reward 4.32988 time 10000.0 params 237.705 0.610095 0.610095 reward 4.97973 time 10000.0 params 226.768 0.591345 0.591345 reward 4.75842 time 10000.0 params 237.705 0.610095 0.610095 reward 5.14130 time 10000.0 params 257.393 0.603845 0.603845 reward 4.10370 time 10000.0 params 237.705 0.610095 0.610095 reward 4.39328 time 10000.0 params 249.737 0.60072 0.60072 reward 2.41183 time 10000.0 params 237.705 0.610095 0.610095 reward 4.50038 time 10000.0 params 247.549 0.60697 0.60697 reward 3.72935 time 10000.0 params 237.705 0.610095 0.610095 reward 4.37817 time 10000.0 params 242.08 0.597595 0.597595 reward 4.87731 time 10000.0 params 247.549 0.60697 0.60697 reward 2.24304 time 10000.0 params 243.174 0.61947 0.61947 reward 3.73979 time 10000.0 params 247.549 0.60697 0.60697 reward 3.56298 time 10000.0 params 253.018 0.616345 0.616345 reward 3.08257 time 10000.0 params 247.549 0.60697 0.60697 reward 4.41088 time 10000.0 params 260.674 0.61947 0.61947 reward 4.12268 time 10000.0 params 253.018 0.616345 0.616345 reward 3.18199 time 10000.0 params 257.393 0.603845 0.603845 reward 2.88624 time 10000.0 params 253.018 0.616345 0.616345 reward 3.56020 time 10000.0 params 246.729 0.615564 0.615564 reward 1.58905 time 10000.0 params 253.018 0.616345 0.616345 reward 3.61515 time 10000.0 params 250.284 0.611658 0.611658 reward 2.17381 time 10000.0 params 253.018 0.616345 0.616345 reward 3.69931 time 10000.0 params 248.096 0.617908 0.617908 reward 3.61642 time 10000.0 params 250.284 0.611658 0.611658 reward 3.76895 time 10000.0 params 255.205 0.610095 0.610095 reward 4.13836 time 10000.0 params 250.284 0.611658 0.611658 reward 4.21698 time 10000.0 params 249.873 0.615955 0.615955 reward 3.71659 time 10000.0 params 250.284 0.611658 0.611658 reward 5.61617 time 10000.0 params 251.651 0.614002 0.614002 reward 3.29564 time 10000.0 params 250.284 0.611658 0.611658 reward 2.66067 time 10000.0 params 249.19 0.614783 0.614783 reward 3.62028 time 10000.0 params 250.284 0.611658 0.611658 reward 5.39019 time 10000.0 params 252.744 0.610877 0.610877 reward 3.14468 time 10000.0 params 250.284 0.611658 0.611658 reward 1.69409 time 10000.0 params 251.377 0.608533 0.608533 reward 2.30065 time 10000.0 params 250.284 0.611658 0.611658 reward 5.06373 time 10000.0 params 251.582 0.612635 0.612635 reward 3.86084 time 10000.0 params 250.284 0.611658 0.611658 reward 2.71015 time 10000.0 params 250.967 0.61283 0.61283 reward 3.70955 time 10000.0 params 250.284 0.611658 0.611658 reward 4.77957 time 10000.0 params 251.514 0.611267 0.611267 reward 3.65104 time 10000.0 params 250.284 0.611658 0.611658 reward 4.13013 time 10000.0 params 250.83 0.610095 0.610095 reward 2.93720 time 10000.0 params 250.284 0.611658 0.611658 reward 5.04935 time 10000.0 params 250.865 0.610779 0.610779 reward 0.73514 time 10000.0 params 250.284 0.611658 0.611658 reward 4.10349 time 10000.0 params 250.557 0.610877 0.610877 reward 4.87788 time 10000.0 params 250.284 0.611658 0.611658 reward 2.12987 time 10000.0 params 250.899 0.611463 0.611463 reward 4.10801 time 10000.0 params 250.284 0.611658 0.611658 reward 4.11449 time 10000.0 params 249.942 0.611072 0.611072 reward 3.61151 time 10000.0 params 250.284 0.611658 0.611658 reward 0.46587 time 10000.0 params 340.194 0.632193 0.632193 reward 3.78384 time 10000.0 params 270.194 0.532193 0.532193 reward 4.57816 time 10000.0 params 270.194 0.632193 0.632193 reward 3.63409 time 10000.0 params 200.194 0.532193 0.532193 reward 3.78282 time 10000.0 params 235.194 0.557193 0.557193 reward 4.83257 time 10000.0 params 305.194 0.607193 0.607193 reward -0.23660 time 10000.0 params 340.194 0.632193 0.632193 reward 0.60257 time 10000.0 params 305.194 0.707193 0.707193 reward 4.29459 time 10000.0 params 278.944 0.575943 0.575943 reward 2.03760 time 10000.0 params 296.444 0.663443 0.663443 reward 3.97126 time 10000.0 params 283.319 0.597818 0.597818 reward 6.02102 time 10000.0 params 292.069 0.591568 0.591568 reward 3.08264 time 10000.0 params 287.694 0.619693 0.619693 reward 2.30516 time 10000.0 params 309.569 0.579068 0.579068 reward 3.68017 time 10000.0 params 293.162 0.609537 0.609537 reward 2.25860 time 10000.0 params 304.1 0.589224 0.589224 reward 3.36018 time 10000.0 params 295.897 0.604458 0.604458 reward 3.14009 time 10000.0 params 298.631 0.59938 0.59938 reward 1.97107 time 10000.0 params 292.615 0.600552 0.600552 reward 2.74347 time 10000.0 params 298.084 0.590396 0.590396 reward 4.26756 time 10000.0 params 296.717 0.592935 0.592935 reward 4.43210 time 10000.0 params 290.154 0.585122 0.585122 reward 4.31499 time 10000.0 params 285.506 0.583755 0.583755 reward 3.11838 time 10000.0 params 288.309 0.58605 0.58605 reward 3.65755 time 10000.0 params 291.111 0.588345 0.588345 reward 0.03780 time 10000.0 params 288.787 0.587662 0.587662 reward 3.66211 time 10000.0 params 294.393 0.592251 0.592251 reward 0.34519 time 10000.0 params 295.35 0.595474 0.595474 reward 2.60828 time 10000.0 params 292.171 0.590127 0.590127 reward 4.45345 time 10000.0 params 291.59 0.589956 0.589956 reward 3.71872 time 10000.0 params 293.231 0.59191 0.59191 reward 4.92671 time 10000.0 params 290.428 0.589615 0.589615 reward 2.78894 time 10000.0 params 290.906 0.591226 0.591226 reward 3.17329 time 10000.0 params 291.419 0.590274 0.590274 reward 3.44165 time 10000.0 params 291.829 0.590762 0.590762 reward 5.03048 time 10000.0 params 291.248 0.590591 0.590591 reward 4.98300 time 10000.0 params 291.487 0.591397 0.591397 reward 1.33667 time 10000.0 params 291.573 0.591238 0.591238 reward 3.73713 time 10000.0 params 291.778 0.591482 0.591482 reward 5.01165 time 10000.0 params 291.658 0.59108 0.59108 reward 1.81119 time 10000.0 params 291.949 0.591165 0.591165 reward 2.41633 time 10000.0 params 291.821 0.591403 0.591403 reward 1.71673 time 10000.0 params 291.923 0.591525 0.591525 reward 4.64707 time 10000.0 params 291.863 0.591324 0.591324 reward 1.42066 time 10000.0 params 340.194 0.632193 0.632193 reward -0.34733 time 10000.0 params 340.194 0.632193 0.632193 reward 4.35539 time 10000.0 params 270.194 0.532193 0.532193 reward 5.36358 time 10000.0 params 340.194 0.632193 0.632193 reward 4.42427 time 10000.0 params 270.194 0.632193 0.632193 reward 3.40038 time 10000.0 params 270.194 0.532193 0.532193 reward 3.46874 time 10000.0 params 200.194 0.532193 0.532193 reward 3.48521 time 10000.0 params 270.194 0.632193 0.632193 reward 4.38344 time 10000.0 params 235.194 0.557193 0.557193 reward 5.04701 time 10000.0 params 270.194 0.632193 0.632193 reward 1.31321 time 10000.0 params 305.194 0.607193 0.607193 reward 2.73145 time 10000.0 params 270.194 0.632193 0.632193 reward 0.44669 time 10000.0 params 340.194 0.632193 0.632193 reward 1.41265 time 10000.0 params 305.194 0.607193 0.607193 reward -0.02480 time 10000.0 params 305.194 0.707193 0.707193 reward 0.67401 time 10000.0 params 305.194 0.607193 0.607193 reward 1.73773 time 10000.0 params 278.944 0.575943 0.575943 reward 2.51635 time 10000.0 params 305.194 0.607193 0.607193 reward 4.02044 time 10000.0 params 296.444 0.663443 0.663443 reward 3.74555 time 10000.0 params 305.194 0.607193 0.607193 reward 3.05812 time 10000.0 params 283.319 0.597818 0.597818 reward 3.48132 time 10000.0 params 305.194 0.607193 0.607193 reward 4.46734 time 10000.0 params 292.069 0.591568 0.591568 reward 1.28990 time 10000.0 params 305.194 0.607193 0.607193 reward 1.86330 time 10000.0 params 287.694 0.619693 0.619693 reward 4.07515 time 10000.0 params 292.069 0.591568 0.591568 reward 2.83653 time 10000.0 params 309.569 0.579068 0.579068 reward 1.81802 time 10000.0 params 292.069 0.591568 0.591568 reward 2.77007 time 10000.0 params 293.162 0.609537 0.609537 reward 2.55436 time 10000.0 params 292.069 0.591568 0.591568 reward 4.40355 time 10000.0 params 304.1 0.589224 0.589224 reward 3.65683 time 10000.0 params 292.069 0.591568 0.591568 reward 1.74598 time 10000.0 params 295.897 0.604458 0.604458 reward 2.82071 time 10000.0 params 292.069 0.591568 0.591568 reward 3.80151 time 10000.0 params 298.631 0.59938 0.59938 reward 2.49299 time 10000.0 params 292.069 0.591568 0.591568 reward 4.25779 time 10000.0 params 292.615 0.600552 0.600552 reward 3.62229 time 10000.0 params 292.069 0.591568 0.591568 reward 2.84831 time 10000.0 params 298.084 0.590396 0.590396 reward 4.16590 time 10000.0 params 292.069 0.591568 0.591568 reward 3.47046 time 10000.0 params 296.717 0.592935 0.592935 reward 3.03192 time 10000.0 params 292.069 0.591568 0.591568 reward 5.20138 time 10000.0 params 290.154 0.585122 0.585122 reward 5.48533 time 10000.0 params 292.069 0.591568 0.591568 reward 4.95438 time 10000.0 params 285.506 0.583755 0.583755 reward 4.71807 time 10000.0 params 292.069 0.591568 0.591568 reward 2.17849 time 10000.0 params 288.309 0.58605 0.58605 reward 5.61103 time 10000.0 params 292.069 0.591568 0.591568 reward 3.62905 time 10000.0 params 291.111 0.588345 0.588345 reward 1.67755 time 10000.0 params 292.069 0.591568 0.591568 reward 1.88606 time 10000.0 params 288.787 0.587662 0.587662 reward 3.66168 time 10000.0 params 292.069 0.591568 0.591568 reward 4.69186 time 10000.0 params 294.393 0.592251 0.592251 reward 1.72503 time 10000.0 params 292.069 0.591568 0.591568 reward 1.68343 time 10000.0 params 295.35 0.595474 0.595474 reward 3.46998 time 10000.0 params 292.069 0.591568 0.591568 reward 0.12220 time 10000.0 params 292.171 0.590127 0.590127 reward 4.03588 time 10000.0 params 292.069 0.591568 0.591568 reward 2.92143 time 10000.0 params 291.59 0.589956 0.589956 reward 2.95170 time 10000.0 params 292.069 0.591568 0.591568 reward 2.57674 time 10000.0 params 293.231 0.59191 0.59191 reward 3.49869 time 10000.0 params 292.069 0.591568 0.591568 reward 2.45291 time 10000.0 params 290.428 0.589615 0.589615 reward 3.49309 time 10000.0 params 292.069 0.591568 0.591568 reward 4.01150 time 10000.0 params 290.906 0.591226 0.591226 reward 1.87340 time 10000.0 params 292.069 0.591568 0.591568 reward 2.78398 time 10000.0 params 291.419 0.590274 0.590274 reward 2.50846 time 10000.0 params 292.069 0.591568 0.591568 reward 3.09311 time 10000.0 params 291.829 0.590762 0.590762 reward 2.24080 time 10000.0 params 292.069 0.591568 0.591568 reward 1.63435 time 10000.0 params 291.248 0.590591 0.590591 reward 4.07782 time 10000.0 params 292.069 0.591568 0.591568 reward 5.41636 time 10000.0 params 291.487 0.591397 0.591397 reward 5.16786 time 10000.0 params 292.069 0.591568 0.591568 reward 2.46609 time 10000.0 params 291.573 0.591238 0.591238 reward 5.20515 time 10000.0 params 292.069 0.591568 0.591568 reward 3.97519 time 10000.0 params 291.778 0.591482 0.591482 reward 3.24512 time 10000.0 params 292.069 0.591568 0.591568 reward 2.58541 time 10000.0 params 291.658 0.59108 0.59108 reward 2.98332 time 10000.0 params 292.069 0.591568 0.591568 reward 4.44955 time 10000.0 params 242.169 0.553624 0.553624 reward 2.93803 time 10000.0 params 172.169 0.453624 0.453624 reward 3.44101 time 10000.0 params 172.169 0.553624 0.553624 reward 3.77206 time 10000.0 params 242.169 0.653624 0.653624 reward 4.19155 time 10000.0 params 312.169 0.653624 0.653624 reward 3.54647 time 10000.0 params 312.169 0.553624 0.553624 reward 4.93187 time 10000.0 params 259.669 0.628624 0.628624 reward 3.37361 time 10000.0 params 189.669 0.528624 0.528624 reward 5.55437 time 10000.0 params 281.544 0.622374 0.622374 reward 2.17678 time 10000.0 params 299.044 0.697374 0.697374 reward 4.40765 time 10000.0 params 256.388 0.589561 0.589561 reward 3.19729 time 10000.0 params 261.857 0.587999 0.587999 reward 2.02470 time 10000.0 params 270.607 0.625499 0.625499 reward 3.76905 time 10000.0 params 272.794 0.584874 0.584874 reward 1.82072 time 10000.0 params 292.482 0.619249 0.619249 reward 3.35925 time 10000.0 params 269.513 0.595811 0.595811 reward 2.89740 time 10000.0 params 284.825 0.611436 0.611436 reward 2.97420 time 10000.0 params 273.341 0.599718 0.599718 reward 2.95108 time 10000.0 params 275.529 0.609093 0.609093 reward 3.49485 time 10000.0 params 277.169 0.603624 0.603624 reward 4.56238 time 10000.0 params 283.185 0.616905 0.616905 reward 3.40979 time 10000.0 params 287.56 0.635655 0.635655 reward 3.02418 time 10000.0 params 279.767 0.611632 0.611632 reward 2.75528 time 10000.0 params 282.364 0.619639 0.619639 reward -0.15010 time 10000.0 params 279.357 0.612999 0.612999 reward 2.22815 time 10000.0 params 284.552 0.629014 0.629014 reward 4.60994 time 10000.0 params 283.253 0.625011 0.625011 reward 2.82789 time 10000.0 params 282.433 0.627745 0.627745 reward 4.72503 time 10000.0 params 282.416 0.625719 0.625719 reward 1.53808 time 10000.0 params 280.707 0.623082 0.623082 reward 1.31021 time 10000.0 params 282.617 0.624528 0.624528 reward 3.04959 time 10000.0 params 281.98 0.624046 0.624046 reward 5.31599 time 10000.0 params 282.399 0.623692 0.623692 reward 3.59268 time 10000.0 params 281.963 0.62202 0.62202 reward 4.11815 time 10000.0 params 281.967 0.622526 0.622526 reward 0.25559 time 10000.0 params 281.976 0.62354 0.62354 reward 2.70464 time 10000.0 params 281.969 0.62278 0.62278 reward 2.12886 time 10000.0 params 281.756 0.62245 0.62245 reward 3.16054 time 10000.0 params 281.971 0.623033 0.623033 reward 2.69616 time 10000.0 params 281.76 0.622957 0.622957 reward 3.26620 time 10000.0 params 281.759 0.62283 0.62283 reward 2.56829 time 10000.0 params 281.332 0.622171 0.622171 reward 3.25357 time 10000.0 params 281.811 0.622817 0.622817 reward 2.06385 time 10000.0 params 281.492 0.622386 0.622386 reward 5.03675 time 10000.0 params 281.731 0.62271 0.62271 reward 4.12598 time 10000.0 params 242.169 0.553624 0.553624 reward 4.01666 time 10000.0 params 242.169 0.553624 0.553624 reward 2.99449 time 10000.0 params 172.169 0.453624 0.453624 reward 4.40749 time 10000.0 params 242.169 0.553624 0.553624 reward 3.48891 time 10000.0 params 172.169 0.553624 0.553624 reward 5.17989 time 10000.0 params 242.169 0.553624 0.553624 reward 5.19378 time 10000.0 params 242.169 0.653624 0.653624 reward 3.47131 time 10000.0 params 242.169 0.553624 0.553624 reward 1.83382 time 10000.0 params 312.169 0.653624 0.653624 reward 4.48881 time 10000.0 params 242.169 0.553624 0.553624 reward 1.59644 time 10000.0 params 312.169 0.553624 0.553624 reward 5.03066 time 10000.0 params 242.169 0.553624 0.553624 reward 3.71477 time 10000.0 params 259.669 0.628624 0.628624 reward 4.73805 time 10000.0 params 242.169 0.553624 0.553624 reward 4.14370 time 10000.0 params 189.669 0.528624 0.528624 reward 0.96950 time 10000.0 params 259.669 0.628624 0.628624 reward 3.63561 time 10000.0 params 281.544 0.622374 0.622374 reward 3.70769 time 10000.0 params 259.669 0.628624 0.628624 reward 3.09529 time 10000.0 params 299.044 0.697374 0.697374 reward 4.43461 time 10000.0 params 281.544 0.622374 0.622374 reward 3.77032 time 10000.0 params 256.388 0.589561 0.589561 reward 4.20016 time 10000.0 params 281.544 0.622374 0.622374 reward 3.60182 time 10000.0 params 261.857 0.587999 0.587999 reward 1.50225 time 10000.0 params 281.544 0.622374 0.622374 reward 2.90014 time 10000.0 params 270.607 0.625499 0.625499 reward 3.08450 time 10000.0 params 281.544 0.622374 0.622374 reward 3.83729 time 10000.0 params 272.794 0.584874 0.584874 reward 5.02788 time 10000.0 params 281.544 0.622374 0.622374 reward 1.85400 time 10000.0 params 292.482 0.619249 0.619249 reward 1.26901 time 10000.0 params 281.544 0.622374 0.622374 reward 5.86913 time 10000.0 params 269.513 0.595811 0.595811 reward 1.43077 time 10000.0 params 281.544 0.622374 0.622374 reward 3.66405 time 10000.0 params 284.825 0.611436 0.611436 reward 3.59238 time 10000.0 params 281.544 0.622374 0.622374 reward 4.38888 time 10000.0 params 273.341 0.599718 0.599718 reward 2.85226 time 10000.0 params 281.544 0.622374 0.622374 reward 4.38338 time 10000.0 params 275.529 0.609093 0.609093 reward 3.60085 time 10000.0 params 281.544 0.622374 0.622374 reward 3.40690 time 10000.0 params 277.169 0.603624 0.603624 reward 2.31124 time 10000.0 params 281.544 0.622374 0.622374 reward 4.84080 time 10000.0 params 283.185 0.616905 0.616905 reward 3.59148 time 10000.0 params 281.544 0.622374 0.622374 reward 2.40158 time 10000.0 params 287.56 0.635655 0.635655 reward 0.36445 time 10000.0 params 281.544 0.622374 0.622374 reward 4.53431 time 10000.0 params 279.767 0.611632 0.611632 reward 0.31277 time 10000.0 params 281.544 0.622374 0.622374 reward 4.98505 time 10000.0 params 282.364 0.619639 0.619639 reward 3.27953 time 10000.0 params 281.544 0.622374 0.622374 reward 3.10528 time 10000.0 params 279.357 0.612999 0.612999 reward 2.99789 time 10000.0 params 281.544 0.622374 0.622374 reward 4.86314 time 10000.0 params 284.552 0.629014 0.629014 reward 4.25951 time 10000.0 params 281.544 0.622374 0.622374 reward 5.06048 time 10000.0 params 283.253 0.625011 0.625011 reward 5.00904 time 10000.0 params 281.544 0.622374 0.622374 reward 3.19990 time 10000.0 params 282.433 0.627745 0.627745 reward 4.26793 time 10000.0 params 281.544 0.622374 0.622374 reward 4.02537 time 10000.0 params 282.416 0.625719 0.625719 reward 4.64895 time 10000.0 params 281.544 0.622374 0.622374 reward 3.40448 time 10000.0 params 280.707 0.623082 0.623082 reward 4.08600 time 10000.0 params 281.544 0.622374 0.622374 reward 3.61684 time 10000.0 params 282.617 0.624528 0.624528 reward 4.67398 time 10000.0 params 281.544 0.622374 0.622374 reward 2.38575 time 10000.0 params 281.98 0.624046 0.624046 reward 2.18564 time 10000.0 params 281.544 0.622374 0.622374 reward 4.04248 time 10000.0 params 282.399 0.623692 0.623692 reward 2.21025 time 10000.0 params 281.544 0.622374 0.622374 reward 1.50365 time 10000.0 params 281.963 0.62202 0.62202 reward 2.52182 time 10000.0 params 281.544 0.622374 0.622374 reward 2.23664 time 10000.0 params 281.967 0.622526 0.622526 reward 2.26333 time 10000.0 params 281.544 0.622374 0.622374 reward 3.65663 time 10000.0 params 281.976 0.62354 0.62354 reward 3.91078 time 10000.0 params 281.544 0.622374 0.622374 reward 3.82265 time 10000.0 params 281.969 0.62278 0.62278 reward 2.28248 time 10000.0 params 281.544 0.622374 0.622374 reward 4.69830 time 10000.0 params 281.756 0.62245 0.62245 reward 2.27676 time 10000.0 params 281.544 0.622374 0.622374 reward 3.01413 time 10000.0 params 281.971 0.623033 0.623033 reward 1.07593 time 10000.0 params 281.544 0.622374 0.622374 reward 1.71458 time 10000.0 params 281.76 0.622957 0.622957 reward 4.58511 time 10000.0 params 281.544 0.622374 0.622374 reward 3.16854 time 10000.0 params 331.24 0.741214 0.741214 reward 4.39538 time 10000.0 params 261.24 0.641214 0.641214 reward 2.93953 time 10000.0 params 261.24 0.741214 0.741214 reward 2.56952 time 10000.0 params 331.24 0.641214 0.641214 reward 5.67436 time 10000.0 params 278.74 0.716214 0.716214 reward 2.48192 time 10000.0 params 208.74 0.616214 0.616214 reward 0.38058 time 10000.0 params 300.615 0.709964 0.709964 reward 2.21258 time 10000.0 params 304.99 0.728714 0.728714 reward 4.56259 time 10000.0 params 269.99 0.678714 0.678714 reward 4.24946 time 10000.0 params 243.74 0.666214 0.666214 reward 2.54540 time 10000.0 params 259.053 0.681839 0.681839 reward 3.05358 time 10000.0 params 261.24 0.691214 0.691214 reward 1.96660 time 10000.0 params 274.365 0.697464 0.697464 reward 2.76860 time 10000.0 params 265.615 0.709964 0.709964 reward 3.03053 time 10000.0 params 267.803 0.706839 0.706839 reward 2.98728 time 10000.0 params 272.178 0.700589 0.700589 reward 4.25068 time 10000.0 params 268.897 0.705277 0.705277 reward 1.91090 time 10000.0 params 286.397 0.730277 0.730277 reward 1.46905 time 10000.0 params 267.529 0.70098 0.70098 reward 3.13257 time 10000.0 params 269.99 0.703714 0.703714 reward 3.16585 time 10000.0 params 273.818 0.710746 0.710746 reward 2.74902 time 10000.0 params 282.568 0.723246 0.723246 reward 2.98170 time 10000.0 params 273.135 0.708597 0.708597 reward 2.53845 time 10000.0 params 274.365 0.709964 0.709964 reward 3.59892 time 10000.0 params 276.279 0.71348 0.71348 reward 3.60739 time 10000.0 params 280.654 0.71973 0.71973 reward 0.68789 time 10000.0 params 283.115 0.722464 0.722464 reward 0.86886 time 10000.0 params 277.988 0.715726 0.715726 reward 2.10315 time 10000.0 params 279.697 0.717972 0.717972 reward 0.04247 time 10000.0 params 277.51 0.714847 0.714847 reward 2.83823 time 10000.0 params 280.928 0.719339 0.719339 reward 1.89303 time 10000.0 params 279.971 0.717582 0.717582 reward 1.60462 time 10000.0 params 279.766 0.717875 0.717875 reward 2.99335 time 10000.0 params 279.219 0.717093 0.717093 reward 1.22956 time 10000.0 params 279.834 0.717777 0.717777 reward 2.67580 time 10000.0 params 278.125 0.715531 0.715531 reward 1.99847 time 10000.0 params 278.552 0.716092 0.716092 reward 0.33823 time 10000.0 params 278.98 0.716654 0.716654 reward -0.00120 time 10000.0 params 278.433 0.715873 0.715873 reward 3.54746 time 10000.0 params 279.287 0.716996 0.716996 reward 3.27033 time 10000.0 params 279.048 0.716556 0.716556 reward 3.50198 time 10000.0 params 279.031 0.716581 0.716581 reward 4.58790 time 10000.0 params 278.997 0.716629 0.716629 reward 1.58569 time 10000.0 params 278.45 0.715848 0.715848 reward 0.85338 time 10000.0 params 279.078 0.716709 0.716709 reward 3.15380 time 10000.0 params 278.868 0.716422 0.716422 reward 6.05888 time 10000.0 params 279.014 0.716605 0.716605 reward 1.60746 time 10000.0 params 331.24 0.741214 0.741214 reward -0.25045 time 10000.0 params 331.24 0.741214 0.741214 reward 2.26068 time 10000.0 params 261.24 0.641214 0.641214 reward -1.91432 time 10000.0 params 331.24 0.741214 0.741214 reward 0.10530 time 10000.0 params 261.24 0.741214 0.741214 reward 3.54262 time 10000.0 params 261.24 0.641214 0.641214 reward 3.65934 time 10000.0 params 331.24 0.641214 0.641214 reward 3.46455 time 10000.0 params 261.24 0.641214 0.641214 reward 2.46743 time 10000.0 params 278.74 0.716214 0.716214 reward 2.08689 time 10000.0 params 261.24 0.641214 0.641214 reward 3.79726 time 10000.0 params 208.74 0.616214 0.616214 reward 1.81101 time 10000.0 params 278.74 0.716214 0.716214 reward 2.36282 time 10000.0 params 300.615 0.709964 0.709964 reward 2.87641 time 10000.0 params 278.74 0.716214 0.716214 reward 2.93087 time 10000.0 params 304.99 0.728714 0.728714 reward 1.18878 time 10000.0 params 278.74 0.716214 0.716214 reward 1.66266 time 10000.0 params 269.99 0.678714 0.678714 reward 0.77600 time 10000.0 params 278.74 0.716214 0.716214 reward 4.29597 time 10000.0 params 243.74 0.666214 0.666214 reward 3.71402 time 10000.0 params 278.74 0.716214 0.716214 reward 0.29629 time 10000.0 params 259.053 0.681839 0.681839 reward 2.98540 time 10000.0 params 278.74 0.716214 0.716214 reward 3.09762 time 10000.0 params 261.24 0.691214 0.691214 reward 2.50430 time 10000.0 params 278.74 0.716214 0.716214 reward 4.57252 time 10000.0 params 274.365 0.697464 0.697464 reward 3.70945 time 10000.0 params 278.74 0.716214 0.716214 reward 3.38700 time 10000.0 params 265.615 0.709964 0.709964 reward 4.16599 time 10000.0 params 278.74 0.716214 0.716214 reward 2.54084 time 10000.0 params 267.803 0.706839 0.706839 reward 2.98501 time 10000.0 params 278.74 0.716214 0.716214 reward 3.97831 time 10000.0 params 272.178 0.700589 0.700589 reward 2.50664 time 10000.0 params 278.74 0.716214 0.716214 reward 2.82583 time 10000.0 params 268.897 0.705277 0.705277 reward -0.68278 time 10000.0 params 278.74 0.716214 0.716214 reward -0.75646 time 10000.0 params 286.397 0.730277 0.730277 reward 2.19944 time 10000.0 params 278.74 0.716214 0.716214 reward 3.40712 time 10000.0 params 267.529 0.70098 0.70098 reward 2.16575 time 10000.0 params 278.74 0.716214 0.716214 reward 1.95449 time 10000.0 params 269.99 0.703714 0.703714 reward 5.06348 time 10000.0 params 278.74 0.716214 0.716214 reward 2.93793 time 10000.0 params 273.818 0.710746 0.710746 reward 2.21904 time 10000.0 params 278.74 0.716214 0.716214 reward 2.18164 time 10000.0 params 282.568 0.723246 0.723246 reward 1.81830 time 10000.0 params 278.74 0.716214 0.716214 reward 0.71374 time 10000.0 params 273.135 0.708597 0.708597 reward 1.17748 time 10000.0 params 278.74 0.716214 0.716214 reward 4.00900 time 10000.0 params 274.365 0.709964 0.709964 reward 2.67269 time 10000.0 params 278.74 0.716214 0.716214 reward 2.38516 time 10000.0 params 276.279 0.71348 0.71348 reward 2.02930 time 10000.0 params 278.74 0.716214 0.716214 reward 3.28407 time 10000.0 params 280.654 0.71973 0.71973 reward 3.67181 time 10000.0 params 278.74 0.716214 0.716214 reward 3.34795 time 10000.0 params 283.115 0.722464 0.722464 reward 2.95418 time 10000.0 params 278.74 0.716214 0.716214 reward 2.88763 time 10000.0 params 277.988 0.715726 0.715726 reward 1.46054 time 10000.0 params 278.74 0.716214 0.716214 reward -0.76718 time 10000.0 params 279.697 0.717972 0.717972 reward 1.36749 time 10000.0 params 278.74 0.716214 0.716214 reward 3.33600 time 10000.0 params 277.51 0.714847 0.714847 reward -0.15780 time 10000.0 params 278.74 0.716214 0.716214 reward -1.72934 time 10000.0 params 280.928 0.719339 0.719339 reward 4.14209 time 10000.0 params 278.74 0.716214 0.716214 reward 2.84097 time 10000.0 params 279.971 0.717582 0.717582 reward 4.70749 time 10000.0 params 278.74 0.716214 0.716214 reward 2.62974 time 10000.0 params 279.766 0.717875 0.717875 reward 3.12106 time 10000.0 params 278.74 0.716214 0.716214 reward 1.75949 time 10000.0 params 279.219 0.717093 0.717093 reward 0.62309 time 10000.0 params 278.74 0.716214 0.716214 reward 2.80189 time 10000.0 params 279.834 0.717777 0.717777 reward 3.04753 time 10000.0 params 278.74 0.716214 0.716214 reward 3.85909 time 10000.0 params 278.125 0.715531 0.715531 reward 2.15273 time 10000.0 params 278.74 0.716214 0.716214 reward 3.50725 time 10000.0 params 278.552 0.716092 0.716092 reward 3.04319 time 10000.0 params 278.74 0.716214 0.716214 reward 3.21793 time 10000.0 params 278.98 0.716654 0.716654 reward 2.44991 time 10000.0 params 278.74 0.716214 0.716214 reward 2.68687 time 10000.0 params 278.433 0.715873 0.715873 reward 2.13840 time 10000.0 params 278.74 0.716214 0.716214 reward 3.17589 time 10000.0 params 279.287 0.716996 0.716996 reward 1.56528 time 10000.0 params 278.74 0.716214 0.716214 reward 4.77604 time 10000.0 params 350 0.5 0.5 reward 1.25902 time 10000.0 params 350 0.5 0.5 reward 3.70687 time 10000.0 params 350 0.5 0.5 reward 0.61779 time 10000.0 params 700 0 0 reward -0.70470 time 10000.0 params 699.379 0.0250273 0.0250273 reward -0.14009 time 10000.0 params 699.379 0.0250273 0.0250273 reward 4.14079 time 10000.0 params 233.126 0.675449 0.675449 reward -0.06050 time 10000.0 params 123.084 0.00972496 0.00972496 reward -0.05480 time 10000.0 params 123.084 0.00972496 0.00972496 reward -15.98932 time 10000.0 params 0 0.633773 0.633773 reward -7.81656 time 10000.0 params 14.2096 0.629084 0.629084 reward -7.79132 time 10000.0 params 14.2096 0.629084 0.629084 reward 2.63099 time 10000.0 params 398.703 0.196493 0.196493 reward -4.16919 time 10000.0 params 699.73 0.535226 0.535226 reward -0.47523 time 10000.0 params 699.73 0.535226 0.535226 reward 1.79867 time 10000.0 params 306.132 0.191142 0.191142 reward 0.30750 time 10000.0 params 301.863 0.859791 0.859791 reward -1.17307 time 10000.0 params 301.863 0.859791 0.859791 reward 2.83206 time 10000.0 params 416.707 0.184114 0.184114 reward 2.27389 time 10000.0 params 419.336 0.169253 0.169253 reward 2.74783 time 10000.0 params 419.336 0.169253 0.169253 reward 1.96385 time 10000.0 params 418.455 0.15671 0.15671 reward 1.56007 time 10000.0 params 428.242 0.170893 0.170893 reward 2.64493 time 10000.0 params 428.242 0.170893 0.170893 reward 1.26585 time 10000.0 params 417.563 0.137705 0.137705 reward 1.72312 time 10000.0 params 416.021 0.126624 0.126624 reward 0.48230 time 10000.0 params 416.021 0.126624 0.126624 reward 2.70230 time 10000.0 params 350 0.5 0.5 reward -7.02693 time 10000.0 params 567.298 0.980434 0.980434 reward -5.12889 time 10000.0 params 567.298 0.980434 0.980434 reward 4.05798 time 10000.0 params 350 0.5 0.5 reward 0.37338 time 10000.0 params 102.226 0.23403 0.23403 reward 0.14210 time 10000.0 params 102.226 0.23403 0.23403 reward 3.67118 time 10000.0 params 350 0.5 0.5 reward 0.93199 time 10000.0 params 667.267 0.393429 0.393429 reward -0.08130 time 10000.0 params 667.267 0.393429 0.393429 reward 2.91070 time 10000.0 params 410.495 0.365411 0.365411 reward -1.55577 time 10000.0 params 465.13 0.736007 0.736007 reward -1.33239 time 10000.0 params 465.13 0.736007 0.736007 reward -15.91553 time 10000.0 params 0 0.518117 0.518117 reward -16.13748 time 10000.0 params 0.139168 0.525641 0.525641 reward -15.81859 time 10000.0 params 0.139168 0.525641 0.525641 reward 3.95884 time 10000.0 params 334.218 0.33842 0.33842 reward 2.98243 time 10000.0 params 581.669 0.160225 0.160225 reward 3.70120 time 10000.0 params 581.669 0.160225 0.160225 reward -15.77275 time 10000.0 params 0 0.517769 0.517769 reward -6.11368 time 10000.0 params 18.8379 0.519784 0.519784 reward -6.12000 time 10000.0 params 18.8379 0.519784 0.519784 reward 4.61662 time 10000.0 params 350 0.5 0.5 reward 1.17569 time 10000.0 params 148.188 0.341081 0.341081 reward 1.20530 time 10000.0 params 148.188 0.341081 0.341081 reward 4.56587 time 10000.0 params 418.501 0.338147 0.338147 reward -2.97366 time 10000.0 params 534.335 0.51561 0.51561 reward 0.24959 time 10000.0 params 534.335 0.51561 0.51561 reward 3.75090 time 10000.0 params 420.337 0.336172 0.336172 reward 3.32052 time 10000.0 params 190.648 0.653157 0.653157 reward 4.22067 time 10000.0 params 190.648 0.653157 0.653157 reward 4.70784 time 10000.0 params 311.391 0.440375 0.440375 reward 3.35700 time 10000.0 params 320.459 0.440938 0.440938 reward 4.88169 time 10000.0 params 320.459 0.440938 0.440938 reward 3.72320 time 10000.0 params 307.353 0.444909 0.444909 reward 4.23819 time 10000.0 params 399.496 0.311745 0.311745 reward 3.27647 time 10000.0 params 399.496 0.311745 0.311745 reward 3.49650 time 10000.0 params 279.776 0.474866 0.474866 reward 4.01447 time 10000.0 params 279.429 0.486575 0.486575 reward 2.54000 time 10000.0 params 279.429 0.486575 0.486575 reward 3.52397 time 10000.0 params 291.666 0.468393 0.468393 reward 0.22288 time 10000.0 params 257.314 0.125522 0.125522 reward -0.21650 time 10000.0 params 257.314 0.125522 0.125522 reward 3.24589 time 10000.0 params 291.666 0.468393 0.468393 reward 4.10189 time 10000.0 params 291.106 0.464138 0.464138 reward 4.00164 time 10000.0 params 291.106 0.464138 0.464138 reward 4.28910 time 10000.0 params 320.459 0.440938 0.440938 reward 0.19928 time 10000.0 params 409.546 0.0232851 0.0232851 reward 0.19927 time 10000.0 params 409.546 0.0232851 0.0232851 reward 3.04785 time 10000.0 params 320.459 0.440938 0.440938 reward 3.25360 time 10000.0 params 124.037 0.876856 0.876856 reward 3.64446 time 10000.0 params 124.037 0.876856 0.876856 reward 4.98067 time 10000.0 params 253.388 0.606963 0.606963 reward 5.04880 time 10000.0 params 246.061 0.609582 0.609582 reward 4.17027 time 10000.0 params 246.061 0.609582 0.609582 reward 5.21695 time 10000.0 params 190.648 0.653157 0.653157 reward -2.26098 time 10000.0 params 384.978 0.719392 0.719392 reward -0.89778 time 10000.0 params 384.978 0.719392 0.719392 reward 3.60461 time 10000.0 params 170.503 0.648545 0.648545 reward 2.73251 time 10000.0 params 549.138 0.368457 0.368457 reward 3.54978 time 10000.0 params 549.138 0.368457 0.368457 reward 2.69019 time 10000.0 params 246.061 0.609582 0.609582 reward 2.54884 time 10000.0 params 298.871 0.738424 0.738424 reward 1.92210 time 10000.0 params 298.871 0.738424 0.738424 reward 4.65910 time 10000.0 params 190.648 0.653157 0.653157 reward 3.50443 time 10000.0 params 484.956 0.244816 0.244816 reward 3.72638 time 10000.0 params 484.956 0.244816 0.244816 reward 4.25164 time 10000.0 params 190.648 0.653157 0.653157 reward -0.48028 time 10000.0 params 45.1006 0.687395 0.687395 reward -0.46655 time 10000.0 params 45.1006 0.687395 0.687395 reward 4.27617 time 10000.0 params 261.724 0.587558 0.587558 reward 2.34653 time 10000.0 params 265.304 0.595509 0.595509 reward 2.82029 time 10000.0 params 265.304 0.595509 0.595509 reward 3.19804 time 10000.0 params 385.758 0.407485 0.407485 reward 4.50734 time 10000.0 params 175.873 0.752456 0.752456 reward 4.62826 time 10000.0 params 175.873 0.752456 0.752456 reward 2.95030 time 10000.0 params 320.459 0.440938 0.440938 reward 4.44750 time 10000.0 params 138.682 0.7747 0.7747 reward 4.57793 time 10000.0 params 138.682 0.7747 0.7747 reward 4.06043 time 10000.0 params 158.029 0.759753 0.759753 reward -7.66586 time 10000.0 params 14.5757 0.998712 0.998712 reward -7.62313 time 10000.0 params 14.5757 0.998712 0.998712 reward 4.06409 time 10000.0 params 138.682 0.7747 0.7747 reward 1.53050 time 10000.0 params 384.684 0.404368 0.404368 reward 2.79904 time 10000.0 params 384.684 0.404368 0.404368 reward 5.15790 time 10000.0 params 158.029 0.759753 0.759753 reward -9.82655 time 10000.0 params 9.73825 0.875105 0.875105 reward -9.80150 time 10000.0 params 9.73825 0.875105 0.875105 reward 4.08649 time 10000.0 params 158.029 0.759753 0.759753 reward 2.90262 time 10000.0 params 115.597 0.665142 0.665142 reward 2.88828 time 10000.0 params 115.597 0.665142 0.665142 reward 4.46300 time 10000.0 params 138.682 0.7747 0.7747 reward 5.07488 time 10000.0 params 396.361 0.335064 0.335064 reward 4.70648 time 10000.0 params 396.361 0.335064 0.335064 reward 3.99334 time 10000.0 params 350 0.5 0.5 reward 1.75843 time 10000.0 params 350 0.5 0.5 reward 3.39816 time 10000.0 params 350 0.5 0.5 reward -0.74846 time 10000.0 params 700 0 0 reward 0.61064 time 10000.0 params 687.249 0.0217923 0.0217923 reward 1.22786 time 10000.0 params 687.249 0.0217923 0.0217923 reward 3.20178 time 10000.0 params 228.922 0.674262 0.674262 reward -12.69015 time 10000.0 params 4.41478 0.038613 0.038613 reward -12.84927 time 10000.0 params 4.41478 0.038613 0.038613 reward -2.81999 time 10000.0 params 488.102 0.655218 0.655218 reward -4.38178 time 10000.0 params 24.674 0.83332 0.83332 reward -4.38590 time 10000.0 params 24.674 0.83332 0.83332 reward -1.68819 time 10000.0 params 700 0.351065 0.351065 reward -3.37251 time 10000.0 params 685.376 0.959506 0.959506 reward -5.65970 time 10000.0 params 685.376 0.959506 0.959506 reward 3.37710 time 10000.0 params 494.811 0.424327 0.424327 reward -1.52259 time 10000.0 params 304.556 0.084593 0.084593 reward -1.00260 time 10000.0 params 304.556 0.084593 0.084593 reward 3.06323 time 10000.0 params 501.153 0.410951 0.410951 reward 3.69772 time 10000.0 params 560.019 0.375907 0.375907 reward 2.75661 time 10000.0 params 560.019 0.375907 0.375907 reward -2.67752 time 10000.0 params 476.241 0.410598 0.410598 reward -0.38939 time 10000.0 params 428.294 0.840305 0.840305 reward -5.69853 time 10000.0 params 428.294 0.840305 0.840305 reward 1.33285 time 10000.0 params 700 0.326593 0.326593 reward -2.67758 time 10000.0 params 656.185 0.66341 0.66341 reward -5.91538 time 10000.0 params 656.185 0.66341 0.66341 reward 3.00725 time 10000.0 params 448.656 0.325396 0.325396 reward 4.17809 time 10000.0 params 414.058 0.261859 0.261859 reward 3.27950 time 10000.0 params 414.058 0.261859 0.261859 reward 3.92674 time 10000.0 params 451.007 0.323578 0.323578 reward 3.58121 time 10000.0 params 456.036 0.329735 0.329735 reward 3.44175 time 10000.0 params 456.036 0.329735 0.329735 reward 3.80115 time 10000.0 params 450.861 0.320322 0.320322 reward -2.56334 time 10000.0 params 32.3778 0.371812 0.371812 reward -2.62871 time 10000.0 params 32.3778 0.371812 0.371812 reward 2.65988 time 10000.0 params 453.424 0.322541 0.322541 reward 1.92311 time 10000.0 params 258.835 0.842863 0.842863 reward 3.81943 time 10000.0 params 258.835 0.842863 0.842863 reward 3.81295 time 10000.0 params 397.965 0.3655 0.3655 reward 2.96724 time 10000.0 params 404.866 0.367905 0.367905 reward 4.98977 time 10000.0 params 404.866 0.367905 0.367905 reward 3.47649 time 10000.0 params 395.176 0.369395 0.369395 reward 3.30300 time 10000.0 params 145.614 0.686496 0.686496 reward 4.14348 time 10000.0 params 145.614 0.686496 0.686496 reward 3.18630 time 10000.0 params 426.79 0.297005 0.297005 reward 0.42760 time 10000.0 params 501.511 0.0590333 0.0590333 reward -0.21909 time 10000.0 params 501.511 0.0590333 0.0590333 reward 2.11560 time 10000.0 params 371.512 0.417419 0.417419 reward 2.63319 time 10000.0 params 368.621 0.406385 0.406385 reward 2.66995 time 10000.0 params 368.621 0.406385 0.406385 reward -0.64760 time 10000.0 params 43.8561 1 1 reward -1.21462 time 10000.0 params 39.7866 0.970137 0.970137 reward -1.19397 time 10000.0 params 39.7866 0.970137 0.970137 reward 3.02833 time 10000.0 params 404.866 0.367905 0.367905 reward -2.75019 time 10000.0 params 31.3916 0.916345 0.916345 reward -2.72949 time 10000.0 params 31.3916 0.916345 0.916345 reward 4.95909 time 10000.0 params 404.866 0.367905 0.367905 reward 1.82032 time 10000.0 params 117.107 0.839975 0.839975 reward 3.21886 time 10000.0 params 117.107 0.839975 0.839975 reward 3.15459 time 10000.0 params 404.866 0.367905 0.367905 reward -0.59561 time 10000.0 params 393.933 0.796343 0.796343 reward -3.51325 time 10000.0 params 393.933 0.796343 0.796343 reward 4.02877 time 10000.0 params 404.866 0.367905 0.367905 reward -0.78802 time 10000.0 params 371.461 0.769213 0.769213 reward -0.41398 time 10000.0 params 371.461 0.769213 0.769213 reward 4.05471 time 10000.0 params 404.866 0.367905 0.367905 reward -0.78894 time 10000.0 params 427.878 0.648131 0.648131 reward 0.85828 time 10000.0 params 427.878 0.648131 0.648131 reward 4.47517 time 10000.0 params 404.866 0.367905 0.367905 reward 2.28428 time 10000.0 params 101.882 0.635263 0.635263 reward 1.94680 time 10000.0 params 101.882 0.635263 0.635263 reward 3.46569 time 10000.0 params 404.866 0.367905 0.367905 reward 3.19592 time 10000.0 params 433.381 0.410064 0.410064 reward 4.18189 time 10000.0 params 433.381 0.410064 0.410064 reward 1.72541 time 10000.0 params 272.099 0.624257 0.624257 reward 2.11949 time 10000.0 params 280.973 0.634295 0.634295 reward 0.15418 time 10000.0 params 280.973 0.634295 0.634295 reward 3.99041 time 10000.0 params 404.866 0.367905 0.367905 reward 3.36032 time 10000.0 params 583.508 0.15712 0.15712 reward 3.34499 time 10000.0 params 583.508 0.15712 0.15712 reward 4.63806 time 10000.0 params 433.381 0.410064 0.410064 reward 2.04466 time 10000.0 params 135.529 0.442795 0.442795 reward 1.83598 time 10000.0 params 135.529 0.442795 0.442795 reward 4.23176 time 10000.0 params 433.381 0.410064 0.410064 reward 1.96186 time 10000.0 params 191.749 0.339003 0.339003 reward 1.70859 time 10000.0 params 191.749 0.339003 0.339003 reward 5.06218 time 10000.0 params 433.381 0.410064 0.410064 reward 1.48638 time 10000.0 params 241.01 0.519853 0.519853 reward 3.84342 time 10000.0 params 241.01 0.519853 0.519853 reward 1.79922 time 10000.0 params 433.381 0.410064 0.410064 reward 4.88349 time 10000.0 params 293.524 0.403345 0.403345 reward 3.96780 time 10000.0 params 293.524 0.403345 0.403345 reward 2.81588 time 10000.0 params 433.381 0.410064 0.410064 reward 1.73436 time 10000.0 params 347.667 0.183916 0.183916 reward 1.42996 time 10000.0 params 347.667 0.183916 0.183916 reward 3.79464 time 10000.0 params 433.381 0.410064 0.410064 reward 2.38458 time 10000.0 params 449.914 0.516341 0.516341 reward 1.56456 time 10000.0 params 449.914 0.516341 0.516341 reward 2.63868 time 10000.0 params 265.207 0.575752 0.575752 reward 1.77836 time 10000.0 params 682.293 0.359448 0.359448 reward 1.56775 time 10000.0 params 682.293 0.359448 0.359448 reward 2.23200 time 10000.0 params 414.058 0.261859 0.261859 reward 2.19901 time 10000.0 params 320.949 0.298951 0.298951 reward 3.05362 time 10000.0 params 320.949 0.298951 0.298951 reward 5.49808 time 10000.0 params 270.446 0.566161 0.566161 reward 4.74739 time 10000.0 params 200.338 0.61826 0.61826 reward 4.71239 time 10000.0 params 200.338 0.61826 0.61826 reward -0.01070 time 10000.0 params 433.381 0.410064 0.410064 reward 1.64718 time 10000.0 params 318.379 0.221382 0.221382 reward 2.09156 time 10000.0 params 318.379 0.221382 0.221382 reward 3.21486 time 10000.0 params 145.614 0.686496 0.686496 reward 2.88079 time 10000.0 params 190.41 0.434084 0.434084 reward 2.96017 time 10000.0 params 190.41 0.434084 0.434084 reward 3.69603 time 10000.0 params 145.614 0.686496 0.686496 reward 4.95387 time 10000.0 params 183.816 0.899909 0.899909 reward 4.87165 time 10000.0 params 183.816 0.899909 0.899909 reward 3.64840 time 10000.0 params 120.344 0.807582 0.807582 reward -0.77562 time 10000.0 params 584.032 0.0158394 0.0158394 reward -0.20337 time 10000.0 params 584.032 0.0158394 0.0158394 reward 3.60892 time 10000.0 params 350 0.5 0.5 reward 4.25341 time 10000.0 params 350 0.5 0.5 reward -0.05269 time 10000.0 params 350 0.5 0.5 reward 0.18119 time 10000.0 params 700 0 0 reward 0.04330 time 10000.0 params 681.368 0.00158303 0.00158303 reward -0.04089 time 10000.0 params 681.368 0.00158303 0.00158303 reward 0.23197 time 10000.0 params 700 0 0 reward 0.26950 time 10000.0 params 107.78 0.0180294 0.0180294 reward 0.64178 time 10000.0 params 107.78 0.0180294 0.0180294 reward -15.91978 time 10000.0 params 0 0 0 reward 0.87962 time 10000.0 params 176.132 0.927433 0.927433 reward 2.80741 time 10000.0 params 176.132 0.927433 0.927433 reward -16.08830 time 10000.0 params 0 1 1 reward -3.56763 time 10000.0 params 529.543 0.893012 0.893012 reward -4.53460 time 10000.0 params 529.543 0.893012 0.893012 reward -15.88407 time 10000.0 params 0 1 1 reward 0.34417 time 10000.0 params 65.1143 0.411727 0.411727 reward 0.82578 time 10000.0 params 65.1143 0.411727 0.411727 reward -16.03976 time 10000.0 params 0 1 1 reward -6.98184 time 10000.0 params 16.6171 0.997223 0.997223 reward -6.69578 time 10000.0 params 16.6171 0.997223 0.997223 reward -0.28224 time 10000.0 params 367.407 0 0 reward -0.39616 time 10000.0 params 376.027 0.017932 0.017932 reward 0.25647 time 10000.0 params 376.027 0.017932 0.017932 reward 4.49496 time 10000.0 params 176.132 0.927433 0.927433 reward 2.20962 time 10000.0 params 90.4238 0.909907 0.909907 reward 2.57880 time 10000.0 params 90.4238 0.909907 0.909907 reward 1.85031 time 10000.0 params 350 0.5 0.5 reward -5.20759 time 10000.0 params 491.635 0.914516 0.914516 reward -2.82463 time 10000.0 params 491.635 0.914516 0.914516 reward 4.23187 time 10000.0 params 113.397 1 1 reward 3.78741 time 10000.0 params 104.946 0.988237 0.988237 reward 4.28067 time 10000.0 params 104.946 0.988237 0.988237 reward 2.69490 time 10000.0 params 214.417 0.330807 0.330807 reward 2.17848 time 10000.0 params 217.972 0.325966 0.325966 reward 2.24432 time 10000.0 params 217.972 0.325966 0.325966 reward 4.95145 time 10000.0 params 350 0.5 0.5 reward 3.86506 time 10000.0 params 549.311 0.25135 0.25135 reward 4.11560 time 10000.0 params 549.311 0.25135 0.25135 reward 2.68918 time 10000.0 params 350 0.5 0.5 reward -2.93989 time 10000.0 params 590.115 0.673215 0.673215 reward -1.93466 time 10000.0 params 590.115 0.673215 0.673215 reward 3.60441 time 10000.0 params 345.473 0.286131 0.286131 reward 4.52665 time 10000.0 params 149.762 0.712852 0.712852 reward 3.93052 time 10000.0 params 149.762 0.712852 0.712852 reward 4.40326 time 10000.0 params 338.44 0.377745 0.377745 reward 3.13960 time 10000.0 params 342.845 0.387883 0.387883 reward 5.49324 time 10000.0 params 342.845 0.387883 0.387883 reward -0.03190 time 10000.0 params 551.046 0 0 reward -0.96880 time 10000.0 params 546.545 0.00503994 0.00503994 reward 0.45518 time 10000.0 params 546.545 0.00503994 0.00503994 reward 3.54763 time 10000.0 params 236.234 0.559915 0.559915 reward 3.73467 time 10000.0 params 239.483 0.567587 0.567587 reward 4.16309 time 10000.0 params 239.483 0.567587 0.567587 reward 3.48429 time 10000.0 params 342.845 0.387883 0.387883 reward 2.49312 time 10000.0 params 284.488 0.446084 0.446084 reward 4.25208 time 10000.0 params 284.488 0.446084 0.446084 reward 4.09687 time 10000.0 params 342.845 0.387883 0.387883 reward 0.12888 time 10000.0 params 488.987 0.0841919 0.0841919 reward 0.62126 time 10000.0 params 488.987 0.0841919 0.0841919 reward 4.91677 time 10000.0 params 342.845 0.387883 0.387883 reward 2.91329 time 10000.0 params 125.066 0.913168 0.913168 reward 3.86670 time 10000.0 params 125.066 0.913168 0.913168 reward 4.00879 time 10000.0 params 342.845 0.387883 0.387883 reward 0.16509 time 10000.0 params 533.046 0.0714859 0.0714859 reward 0.05409 time 10000.0 params 533.046 0.0714859 0.0714859 reward 4.46796 time 10000.0 params 342.845 0.387883 0.387883 reward 2.99908 time 10000.0 params 368.328 0.253398 0.253398 reward 3.16636 time 10000.0 params 368.328 0.253398 0.253398 reward 3.11398 time 10000.0 params 350 0.5 0.5 reward -3.82497 time 10000.0 params 337.145 0.92619 0.92619 reward -0.53294 time 10000.0 params 337.145 0.92619 0.92619 reward 4.88145 time 10000.0 params 342.845 0.387883 0.387883 reward 3.81379 time 10000.0 params 361.276 0.449125 0.449125 reward 1.98464 time 10000.0 params 361.276 0.449125 0.449125 reward 3.51194 time 10000.0 params 342.845 0.387883 0.387883 reward 4.02088 time 10000.0 params 185.388 0.922453 0.922453 reward 4.53201 time 10000.0 params 185.388 0.922453 0.922453 reward -15.53759 time 10000.0 params 0 0.826695 0.826695 reward -10.26302 time 10000.0 params 8.47959 0.821046 0.821046 reward -10.41120 time 10000.0 params 8.47959 0.821046 0.821046 reward 4.53720 time 10000.0 params 249.333 0.548063 0.548063 reward 1.87214 time 10000.0 params 149.775 0.409704 0.409704 reward 1.76291 time 10000.0 params 149.775 0.409704 0.409704 reward 4.18368 time 10000.0 params 249.333 0.548063 0.548063 reward 1.80233 time 10000.0 params 89.0267 0.591703 0.591703 reward 1.08375 time 10000.0 params 89.0267 0.591703 0.591703 reward 3.80223 time 10000.0 params 134.295 0.767379 0.767379 reward 3.27496 time 10000.0 params 134.035 0.752521 0.752521 reward 2.85642 time 10000.0 params 134.035 0.752521 0.752521 reward 4.45618 time 10000.0 params 230.288 0.650822 0.650822 reward 2.76315 time 10000.0 params 263.004 0.697255 0.697255 reward 2.18310 time 10000.0 params 263.004 0.697255 0.697255 reward 3.44742 time 10000.0 params 149.762 0.712852 0.712852 reward -3.30858 time 10000.0 params 513.255 0.624894 0.624894 reward -0.91463 time 10000.0 params 513.255 0.624894 0.624894 reward 3.44198 time 10000.0 params 149.762 0.712852 0.712852 reward -1.68456 time 10000.0 params 396.673 0.76534 0.76534 reward 0.89636 time 10000.0 params 396.673 0.76534 0.76534 reward 5.49916 time 10000.0 params 342.845 0.387883 0.387883 reward 2.97060 time 10000.0 params 283.085 0.294312 0.294312 reward 2.90073 time 10000.0 params 283.085 0.294312 0.294312 reward 3.39188 time 10000.0 params 243.905 0.596412 0.596412 reward 4.87677 time 10000.0 params 186.191 0.789387 0.789387 reward 4.88663 time 10000.0 params 186.191 0.789387 0.789387 reward 3.51152 time 10000.0 params 342.845 0.387883 0.387883 reward 2.69497 time 10000.0 params 433.708 0.221216 0.221216 reward 1.26178 time 10000.0 params 433.708 0.221216 0.221216 reward 4.04430 time 10000.0 params 233.341 0.628868 0.628868 reward 5.04672 time 10000.0 params 236.946 0.641305 0.641305 reward 3.49577 time 10000.0 params 236.946 0.641305 0.641305 reward 2.43758 time 10000.0 params 230.089 0.632823 0.632823 reward 2.29598 time 10000.0 params 224.337 0.628588 0.628588 reward 4.24030 time 10000.0 params 224.337 0.628588 0.628588 reward 3.77536 time 10000.0 params 342.845 0.387883 0.387883 reward 3.17708 time 10000.0 params 414.42 0.218555 0.218555 reward 2.71207 time 10000.0 params 414.42 0.218555 0.218555 reward 4.07433 time 10000.0 params 342.845 0.387883 0.387883 reward 2.96788 time 10000.0 params 135.382 0.84486 0.84486 reward 3.49532 time 10000.0 params 135.382 0.84486 0.84486 reward 3.15843 time 10000.0 params 350 0.5 0.5 reward 2.32735 time 10000.0 params 350 0.5 0.5 reward 2.08739 time 10000.0 params 350 0.5 0.5 reward 0.45756 time 10000.0 params 700 0 0 reward 0.30620 time 10000.0 params 699.199 0.0157148 0.0157148 reward -0.81189 time 10000.0 params 699.199 0.0157148 0.0157148 reward 3.81239 time 10000.0 params 233.066 0.672075 0.672075 reward -3.89437 time 10000.0 params 653.741 0.907504 0.907504 reward -4.80164 time 10000.0 params 653.741 0.907504 0.907504 reward 2.20949 time 10000.0 params 186.327 0.359204 0.359204 reward 0.16305 time 10000.0 params 65.0566 0.0724868 0.0724868 reward 0.69579 time 10000.0 params 65.0566 0.0724868 0.0724868 reward 3.84006 time 10000.0 params 225.891 0.404378 0.404378 reward -8.80297 time 10000.0 params 11.7667 0.909267 0.909267 reward -8.70465 time 10000.0 params 11.7667 0.909267 0.909267 reward 0.65888 time 10000.0 params 351.739 0 0 reward 0.69143 time 10000.0 params 408.338 0.019598 0.019598 reward 0.37130 time 10000.0 params 408.338 0.019598 0.019598 reward 2.78941 time 10000.0 params 456.012 0.34126 0.34126 reward 2.40384 time 10000.0 params 516.008 0.364552 0.364552 reward 3.35273 time 10000.0 params 516.008 0.364552 0.364552 reward 2.51217 time 10000.0 params 478.858 0.349769 0.349769 reward 2.24642 time 10000.0 params 469.104 0.339057 0.339057 reward 5.11989 time 10000.0 params 469.104 0.339057 0.339057 reward 4.51408 time 10000.0 params 490.532 0.361256 0.361256 reward 2.12919 time 10000.0 params 420.032 0.322199 0.322199 reward 3.01010 time 10000.0 params 420.032 0.322199 0.322199 reward -2.36505 time 10000.0 params 700 0.404787 0.404787 reward -2.05656 time 10000.0 params 693.283 0.417931 0.417931 reward -1.47947 time 10000.0 params 693.283 0.417931 0.417931 reward 3.55811 time 10000.0 params 302.843 0.373785 0.373785 reward 4.08384 time 10000.0 params 310.168 0.383035 0.383035 reward 4.91288 time 10000.0 params 310.168 0.383035 0.383035 reward 3.44827 time 10000.0 params 359.556 0.301773 0.301773 reward -4.02790 time 10000.0 params 533.119 0.65284 0.65284 reward -0.80944 time 10000.0 params 533.119 0.65284 0.65284 reward 4.54343 time 10000.0 params 266.006 0.396319 0.396319 reward 4.04869 time 10000.0 params 263.708 0.409548 0.409548 reward 3.68643 time 10000.0 params 263.708 0.409548 0.409548 reward 1.48522 time 10000.0 params 212.837 0.306556 0.306556 reward 2.42753 time 10000.0 params 214.862 0.838118 0.838118 reward 3.70238 time 10000.0 params 214.862 0.838118 0.838118 reward -15.83049 time 10000.0 params 0 0.813915 0.813915 reward -12.24691 time 10000.0 params 5.175 0.828592 0.828592 reward -12.38054 time 10000.0 params 5.175 0.828592 0.828592 reward -15.86432 time 10000.0 params 0 0.799225 0.799225 reward -5.56384 time 10000.0 params 20.8846 0.803458 0.803458 reward -5.48309 time 10000.0 params 20.8846 0.803458 0.803458 reward 4.10314 time 10000.0 params 263.708 0.409548 0.409548 reward 0.21418 time 10000.0 params 51.73 0.727788 0.727788 reward 0.29719 time 10000.0 params 51.73 0.727788 0.727788 reward 3.22479 time 10000.0 params 263.708 0.409548 0.409548 reward 0.90026 time 10000.0 params 694.387 0.0459054 0.0459054 reward -0.05420 time 10000.0 params 694.387 0.0459054 0.0459054 reward 1.67040 time 10000.0 params 352.789 0.488413 0.488413 reward -0.41118 time 10000.0 params 347.459 0.646879 0.646879 reward 2.47214 time 10000.0 params 347.459 0.646879 0.646879 reward 3.39270 time 10000.0 params 374.703 0.4411 0.4411 reward 4.02980 time 10000.0 params 381.917 0.449901 0.449901 reward 4.13086 time 10000.0 params 381.917 0.449901 0.449901 reward 4.30539 time 10000.0 params 469.104 0.339057 0.339057 reward 2.21332 time 10000.0 params 503.808 0.130989 0.130989 reward 2.11932 time 10000.0 params 503.808 0.130989 0.130989 reward 4.69107 time 10000.0 params 469.104 0.339057 0.339057 reward 1.43903 time 10000.0 params 308.749 0.167294 0.167294 reward 0.09299 time 10000.0 params 308.749 0.167294 0.167294 reward 3.22487 time 10000.0 params 469.104 0.339057 0.339057 reward 1.17568 time 10000.0 params 318.889 0.160033 0.160033 reward 1.13428 time 10000.0 params 318.889 0.160033 0.160033 reward 3.04004 time 10000.0 params 469.104 0.339057 0.339057 reward 1.66045 time 10000.0 params 296.522 0.192377 0.192377 reward 1.26778 time 10000.0 params 296.522 0.192377 0.192377 reward 3.65576 time 10000.0 params 469.104 0.339057 0.339057 reward -2.65537 time 10000.0 params 335.966 0.999934 0.999934 reward -0.55950 time 10000.0 params 335.966 0.999934 0.999934 reward 2.84708 time 10000.0 params 469.104 0.339057 0.339057 reward -0.29397 time 10000.0 params 398.784 0.913874 0.913874 reward -2.43776 time 10000.0 params 398.784 0.913874 0.913874 reward 5.64301 time 10000.0 params 469.104 0.339057 0.339057 reward 4.60775 time 10000.0 params 221.737 0.615323 0.615323 reward 4.58140 time 10000.0 params 221.737 0.615323 0.615323 reward 3.90368 time 10000.0 params 469.104 0.339057 0.339057 reward -3.37060 time 10000.0 params 450.848 0.786844 0.786844 reward -3.59140 time 10000.0 params 450.848 0.786844 0.786844 reward 2.63439 time 10000.0 params 469.104 0.339057 0.339057 reward -3.73947 time 10000.0 params 483.613 0.702116 0.702116 reward -1.56669 time 10000.0 params 483.613 0.702116 0.702116 reward 3.78166 time 10000.0 params 469.104 0.339057 0.339057 reward -0.63329 time 10000.0 params 476.622 0.704135 0.704135 reward -4.32903 time 10000.0 params 476.622 0.704135 0.704135 reward 1.89145 time 10000.0 params 469.104 0.339057 0.339057 reward 2.13975 time 10000.0 params 277.961 0.233403 0.233403 reward 2.25440 time 10000.0 params 277.961 0.233403 0.233403 reward 4.64412 time 10000.0 params 221.737 0.615323 0.615323 reward 1.44665 time 10000.0 params 162.573 0.324801 0.324801 reward 1.12369 time 10000.0 params 162.573 0.324801 0.324801 reward 4.26670 time 10000.0 params 221.737 0.615323 0.615323 reward 3.35611 time 10000.0 params 620.693 0.20582 0.20582 reward 4.24886 time 10000.0 params 620.693 0.20582 0.20582 reward 4.06129 time 10000.0 params 221.737 0.615323 0.615323 reward 3.13690 time 10000.0 params 94.4767 0.907522 0.907522 reward 3.35253 time 10000.0 params 94.4767 0.907522 0.907522 reward 3.98594 time 10000.0 params 310.168 0.383035 0.383035 reward 4.87890 time 10000.0 params 178.111 0.943059 0.943059 reward 0.03390 time 10000.0 params 178.111 0.943059 0.943059 reward 4.53977 time 10000.0 params 310.168 0.383035 0.383035 reward 2.12599 time 10000.0 params 130.598 0.49625 0.49625 reward 1.65971 time 10000.0 params 130.598 0.49625 0.49625 reward 3.03485 time 10000.0 params 310.168 0.383035 0.383035 reward 4.81288 time 10000.0 params 301.88 0.369407 0.369407 reward 4.15635 time 10000.0 params 301.88 0.369407 0.369407 reward 3.05646 time 10000.0 params 310.168 0.383035 0.383035 reward 2.12724 time 10000.0 params 405.373 0.183991 0.183991 reward 2.80675 time 10000.0 params 405.373 0.183991 0.183991 reward 3.80269 time 10000.0 params 469.104 0.339057 0.339057 reward -1.81245 time 10000.0 params 443.807 0.527459 0.527459 reward 0.19109 time 10000.0 params 443.807 0.527459 0.527459 reward 4.31509 time 10000.0 params 469.104 0.339057 0.339057 reward 3.66669 time 10000.0 params 354.689 0.346158 0.346158 reward 3.68335 time 10000.0 params 354.689 0.346158 0.346158 reward 4.02828 time 10000.0 params 350 0.5 0.5 reward 2.39494 time 10000.0 params 350 0.5 0.5 reward 3.57491 time 10000.0 params 350 0.5 0.5 reward -0.13479 time 10000.0 params 700 0 0 reward -0.03350 time 10000.0 params 699.205 0.0221587 0.0221587 reward -0.11170 time 10000.0 params 699.205 0.0221587 0.0221587 reward 2.33666 time 10000.0 params 233.068 0.674395 0.674395 reward -6.50802 time 10000.0 params 17.7568 0.255121 0.255121 reward -6.49680 time 10000.0 params 17.7568 0.255121 0.255121 reward -5.18429 time 10000.0 params 446.386 0.862168 0.862168 reward -3.40369 time 10000.0 params 648.547 0.796246 0.796246 reward -6.07112 time 10000.0 params 648.547 0.796246 0.796246 reward 5.27029 time 10000.0 params 402.579 0.3196 0.3196 reward 2.24154 time 10000.0 params 141.062 0.888962 0.888962 reward 3.73233 time 10000.0 params 141.062 0.888962 0.888962 reward 3.72282 time 10000.0 params 184.372 1 1 reward 0.92101 time 10000.0 params 396.605 0.0415868 0.0415868 reward 0.43850 time 10000.0 params 396.605 0.0415868 0.0415868 reward 3.09206 time 10000.0 params 232.529 0.74155 0.74155 reward 2.59673 time 10000.0 params 133.387 0.534986 0.534986 reward 2.58908 time 10000.0 params 133.387 0.534986 0.534986 reward 4.68860 time 10000.0 params 250.919 0.687825 0.687825 reward -1.57609 time 10000.0 params 356.561 0.952176 0.952176 reward 1.11537 time 10000.0 params 356.561 0.952176 0.952176 reward 4.21508 time 10000.0 params 208.442 0.739076 0.739076 reward 3.83575 time 10000.0 params 211.633 0.742051 0.742051 reward 1.35157 time 10000.0 params 211.633 0.742051 0.742051 reward 3.06453 time 10000.0 params 250.357 0.699264 0.699264 reward 1.27497 time 10000.0 params 662.038 0.376394 0.376394 reward -0.12409 time 10000.0 params 662.038 0.376394 0.376394 reward 1.87715 time 10000.0 params 273.044 0.652002 0.652002 reward 1.00641 time 10000.0 params 241.289 0.191813 0.191813 reward 1.33161 time 10000.0 params 241.289 0.191813 0.191813 reward 3.70940 time 10000.0 params 169.089 0.724824 0.724824 reward 4.32289 time 10000.0 params 582.011 0.192287 0.192287 reward 3.37720 time 10000.0 params 582.011 0.192287 0.192287 reward 2.57545 time 10000.0 params 289.769 0.581984 0.581984 reward 3.71431 time 10000.0 params 297.615 0.575413 0.575413 reward 4.55176 time 10000.0 params 297.615 0.575413 0.575413 reward -0.67187 time 10000.0 params 515.243 0 0 reward -0.37460 time 10000.0 params 506.356 0.0180652 0.0180652 reward -1.61999 time 10000.0 params 506.356 0.0180652 0.0180652 reward 2.73503 time 10000.0 params 297.615 0.575413 0.575413 reward -0.38325 time 10000.0 params 522.387 0.698217 0.698217 reward -2.82304 time 10000.0 params 522.387 0.698217 0.698217 reward 2.18233 time 10000.0 params 297.615 0.575413 0.575413 reward 3.56306 time 10000.0 params 463.707 0.258635 0.258635 reward 3.63244 time 10000.0 params 463.707 0.258635 0.258635 reward 5.19383 time 10000.0 params 350 0.5 0.5 reward 2.91709 time 10000.0 params 234.911 0.396058 0.396058 reward 3.88924 time 10000.0 params 234.911 0.396058 0.396058 reward 2.59913 time 10000.0 params 261.031 0.544034 0.544034 reward 0.35905 time 10000.0 params 497.411 0.505016 0.505016 reward 0.44636 time 10000.0 params 497.411 0.505016 0.505016 reward 5.41769 time 10000.0 params 232.16 0.617549 0.617549 reward 0.14127 time 10000.0 params 349.94 0.759208 0.759208 reward 3.72190 time 10000.0 params 349.94 0.759208 0.759208 reward 4.23013 time 10000.0 params 254.584 0.601458 0.601458 reward 1.19447 time 10000.0 params 78.1472 0.683355 0.683355 reward 1.38457 time 10000.0 params 78.1472 0.683355 0.683355 reward 3.51754 time 10000.0 params 297.615 0.575413 0.575413 reward 3.24090 time 10000.0 params 690.513 0.228867 0.228867 reward 1.45510 time 10000.0 params 690.513 0.228867 0.228867 reward 2.06794 time 10000.0 params 297.615 0.575413 0.575413 reward 2.50070 time 10000.0 params 431.332 0.634817 0.634817 reward -2.28465 time 10000.0 params 431.332 0.634817 0.634817 reward 5.26616 time 10000.0 params 297.615 0.575413 0.575413 reward 3.57931 time 10000.0 params 225.075 0.891656 0.891656 reward 2.68015 time 10000.0 params 225.075 0.891656 0.891656 reward 4.21908 time 10000.0 params 297.615 0.575413 0.575413 reward 3.97588 time 10000.0 params 225.893 0.672423 0.672423 reward 3.40691 time 10000.0 params 225.893 0.672423 0.672423 reward 4.89241 time 10000.0 params 183.915 0.694315 0.694315 reward 0.70337 time 10000.0 params 56.9994 0.886356 0.886356 reward 0.28227 time 10000.0 params 56.9994 0.886356 0.886356 reward 2.63554 time 10000.0 params 463.707 0.258635 0.258635 reward 0.91448 time 10000.0 params 436.326 0.113208 0.113208 reward 1.06374 time 10000.0 params 436.326 0.113208 0.113208 reward 0.69573 time 10000.0 params 329.243 0.456509 0.456509 reward -11.32755 time 10000.0 params 6.70583 0.80223 0.80223 reward -11.59319 time 10000.0 params 6.70583 0.80223 0.80223 reward 2.66390 time 10000.0 params 350 0.5 0.5 reward 2.98042 time 10000.0 params 339.708 0.345562 0.345562 reward 3.57754 time 10000.0 params 339.708 0.345562 0.345562 reward 2.75416 time 10000.0 params 328.991 0.457711 0.457711 reward 2.53730 time 10000.0 params 424.693 0.469936 0.469936 reward 1.50999 time 10000.0 params 424.693 0.469936 0.469936 reward 4.64776 time 10000.0 params 350 0.5 0.5 reward -0.26689 time 10000.0 params 427.589 0.640708 0.640708 reward 0.27920 time 10000.0 params 427.589 0.640708 0.640708 reward 3.65339 time 10000.0 params 278.375 0.572114 0.572114 reward 1.71559 time 10000.0 params 356.75 0.161605 0.161605 reward 1.34016 time 10000.0 params 356.75 0.161605 0.161605 reward 3.60461 time 10000.0 params 350 0.5 0.5 reward 1.85266 time 10000.0 params 391.874 0.688255 0.688255 reward 1.44625 time 10000.0 params 391.874 0.688255 0.688255 reward 3.91549 time 10000.0 params 339.708 0.345562 0.345562 reward 3.03320 time 10000.0 params 410.805 0.207138 0.207138 reward 3.09673 time 10000.0 params 410.805 0.207138 0.207138 reward 2.98319 time 10000.0 params 328.752 0.512131 0.512131 reward 3.55377 time 10000.0 params 403.357 0.338174 0.338174 reward 4.74156 time 10000.0 params 403.357 0.338174 0.338174 reward 2.74403 time 10000.0 params 463.707 0.258635 0.258635 reward 3.92193 time 10000.0 params 145.147 0.656187 0.656187 reward 3.49381 time 10000.0 params 145.147 0.656187 0.656187 reward 3.99639 time 10000.0 params 283.992 0.462124 0.462124 reward 1.28276 time 10000.0 params 494.695 0.361767 0.361767 reward 4.18878 time 10000.0 params 494.695 0.361767 0.361767 reward 3.54738 time 10000.0 params 283.992 0.462124 0.462124 reward 4.43439 time 10000.0 params 289.59 0.461067 0.461067 reward 3.08239 time 10000.0 params 289.59 0.461067 0.461067 reward 5.14770 time 10000.0 params 297.615 0.575413 0.575413 reward 3.28569 time 10000.0 params 269.749 0.331969 0.331969 reward 2.75108 time 10000.0 params 269.749 0.331969 0.331969 reward 5.51739 time 10000.0 params 297.615 0.575413 0.575413 reward 3.79454 time 10000.0 params 276.753 0.647363 0.647363 reward 0.91138 time 10000.0 params 276.753 0.647363 0.647363 reward 3.27371 time 10000.0 params 297.615 0.575413 0.575413 reward 2.92723 time 10000.0 params 364.325 0.232071 0.232071 reward 3.03747 time 10000.0 params 364.325 0.232071 0.232071 reward 3.19169 time 10000.0 params 350 0.5 0.5 reward -0.62839 time 10000.0 params 350 0.5 0.5 reward 3.14630 time 10000.0 params 350 0.5 0.5 reward -0.14808 time 10000.0 params 700 0 0 reward -0.09760 time 10000.0 params 679.618 0.0155447 0.0155447 reward 0.60007 time 10000.0 params 679.618 0.0155447 0.0155447 reward 3.15343 time 10000.0 params 226.119 0.672014 0.672014 reward -1.38474 time 10000.0 params 39.0372 0.959768 0.959768 reward -1.35799 time 10000.0 params 39.0372 0.959768 0.959768 reward 1.99050 time 10000.0 params 404.22 0.423703 0.423703 reward -2.81093 time 10000.0 params 31.4633 0.459277 0.459277 reward -2.71967 time 10000.0 params 31.4633 0.459277 0.459277 reward -3.53286 time 10000.0 params 477.73 1 1 reward -2.54818 time 10000.0 params 646.06 0.855763 0.855763 reward -4.40669 time 10000.0 params 646.06 0.855763 0.855763 reward 0.15499 time 10000.0 params 359.408 0 0 reward 1.01380 time 10000.0 params 119.504 0.0254986 0.0254986 reward 0.08620 time 10000.0 params 119.504 0.0254986 0.0254986 reward 0.79548 time 10000.0 params 409.328 0 0 reward -0.48728 time 10000.0 params 403.187 0.0143251 0.0143251 reward 0.41878 time 10000.0 params 403.187 0.0143251 0.0143251 reward 1.97333 time 10000.0 params 401.355 0.175486 0.175486 reward -1.98080 time 10000.0 params 382.689 0.925537 0.925537 reward -3.80333 time 10000.0 params 382.689 0.925537 0.925537 reward 3.28971 time 10000.0 params 418.718 0.19882 0.19882 reward 2.21492 time 10000.0 params 280.995 0.232467 0.232467 reward 1.37799 time 10000.0 params 280.995 0.232467 0.232467 reward 3.66654 time 10000.0 params 350 0.5 0.5 reward 0.65288 time 10000.0 params 553.235 0.359856 0.359856 reward 1.39067 time 10000.0 params 553.235 0.359856 0.359856 reward 3.85249 time 10000.0 params 419.737 0.218676 0.218676 reward 3.73430 time 10000.0 params 194.775 0.711505 0.711505 reward 0.37105 time 10000.0 params 194.775 0.711505 0.711505 reward 1.38955 time 10000.0 params 553.235 0.359856 0.359856 reward -6.59639 time 10000.0 params 17.717 0.772966 0.772966 reward -6.42804 time 10000.0 params 17.717 0.772966 0.772966 reward 3.96819 time 10000.0 params 412.36 0.280441 0.280441 reward 3.60643 time 10000.0 params 417.083 0.284582 0.284582 reward 4.54169 time 10000.0 params 417.083 0.284582 0.284582 reward 3.59236 time 10000.0 params 416.568 0.295244 0.295244 reward 0.60867 time 10000.0 params 136.239 0.334373 0.334373 reward 1.83078 time 10000.0 params 136.239 0.334373 0.334373 reward 3.15422 time 10000.0 params 351.14 0.344133 0.344133 reward -2.71635 time 10000.0 params 679.324 0.600348 0.600348 reward -3.05238 time 10000.0 params 679.324 0.600348 0.600348 reward 4.65789 time 10000.0 params 351.14 0.344133 0.344133 reward 2.99791 time 10000.0 params 358.406 0.329511 0.329511 reward 4.87706 time 10000.0 params 358.406 0.329511 0.329511 reward 2.16192 time 10000.0 params 350.016 0.343371 0.343371 reward 5.01939 time 10000.0 params 328.036 0.37798 0.37798 reward 4.74346 time 10000.0 params 328.036 0.37798 0.37798 reward 3.59330 time 10000.0 params 348.771 0.344141 0.344141 reward 4.65589 time 10000.0 params 357.309 0.342626 0.342626 reward 3.29493 time 10000.0 params 357.309 0.342626 0.342626 reward 4.52986 time 10000.0 params 348.674 0.345172 0.345172 reward -4.31559 time 10000.0 params 541.407 0.699606 0.699606 reward -5.04806 time 10000.0 params 541.407 0.699606 0.699606 reward 4.21383 time 10000.0 params 348.674 0.345172 0.345172 reward 3.81889 time 10000.0 params 356.539 0.354708 0.354708 reward 3.69648 time 10000.0 params 356.539 0.354708 0.354708 reward 3.84827 time 10000.0 params 328.036 0.37798 0.37798 reward 1.96098 time 10000.0 params 516.478 0.164433 0.164433 reward 2.94887 time 10000.0 params 516.478 0.164433 0.164433 reward 4.24938 time 10000.0 params 328.036 0.37798 0.37798 reward 2.61753 time 10000.0 params 250.114 0.537361 0.537361 reward 4.00186 time 10000.0 params 250.114 0.537361 0.537361 reward 4.61881 time 10000.0 params 328.036 0.37798 0.37798 reward 3.48586 time 10000.0 params 199.184 0.469856 0.469856 reward 4.02526 time 10000.0 params 199.184 0.469856 0.469856 reward 4.77204 time 10000.0 params 328.036 0.37798 0.37798 reward 2.26731 time 10000.0 params 499.442 0.417564 0.417564 reward 2.38821 time 10000.0 params 499.442 0.417564 0.417564 reward 4.32194 time 10000.0 params 328.036 0.37798 0.37798 reward 3.68557 time 10000.0 params 329.029 0.634566 0.634566 reward 0.26839 time 10000.0 params 329.029 0.634566 0.634566 reward 3.36310 time 10000.0 params 328.036 0.37798 0.37798 reward 2.25894 time 10000.0 params 467.537 0.446647 0.446647 reward -0.39279 time 10000.0 params 467.537 0.446647 0.446647 reward 3.68549 time 10000.0 params 328.036 0.37798 0.37798 reward 3.41388 time 10000.0 params 200.339 0.423465 0.423465 reward 2.93097 time 10000.0 params 200.339 0.423465 0.423465 reward 3.98500 time 10000.0 params 320.995 0.39623 0.39623 reward 2.93002 time 10000.0 params 312.932 0.411121 0.411121 reward 3.42252 time 10000.0 params 312.932 0.411121 0.411121 reward 4.24059 time 10000.0 params 328.036 0.37798 0.37798 reward 2.37500 time 10000.0 params 320.48 0.227936 0.227936 reward 2.72125 time 10000.0 params 320.48 0.227936 0.227936 reward 4.10860 time 10000.0 params 328.036 0.37798 0.37798 reward 3.84722 time 10000.0 params 504.401 0.323131 0.323131 reward 4.83385 time 10000.0 params 504.401 0.323131 0.323131 reward 3.50338 time 10000.0 params 504.401 0.323131 0.323131 reward 2.99549 time 10000.0 params 617.701 0.156015 0.156015 reward 4.11757 time 10000.0 params 617.701 0.156015 0.156015 reward 3.01489 time 10000.0 params 504.401 0.323131 0.323131 reward 4.07441 time 10000.0 params 640.86 0.256553 0.256553 reward 3.45458 time 10000.0 params 640.86 0.256553 0.256553 reward 3.83131 time 10000.0 params 504.401 0.323131 0.323131 reward 4.06028 time 10000.0 params 261.435 0.453417 0.453417 reward 3.17728 time 10000.0 params 261.435 0.453417 0.453417 reward 4.32814 time 10000.0 params 504.401 0.323131 0.323131 reward 2.78220 time 10000.0 params 588.395 0.208137 0.208137 reward 3.75532 time 10000.0 params 588.395 0.208137 0.208137 reward 3.59800 time 10000.0 params 358.406 0.329511 0.329511 reward 3.94414 time 10000.0 params 363.069 0.28182 0.28182 reward 3.34988 time 10000.0 params 363.069 0.28182 0.28182 reward 4.41815 time 10000.0 params 358.406 0.329511 0.329511 reward 2.71924 time 10000.0 params 589.486 0.3331 0.3331 reward 2.94004 time 10000.0 params 589.486 0.3331 0.3331 reward 3.04783 time 10000.0 params 358.406 0.329511 0.329511 reward 1.90892 time 10000.0 params 550.997 0.330849 0.330849 reward 2.91851 time 10000.0 params 550.997 0.330849 0.330849 reward 3.53011 time 10000.0 params 358.406 0.329511 0.329511 reward 3.15919 time 10000.0 params 508.343 0.26291 0.26291 reward 5.33152 time 10000.0 params 508.343 0.26291 0.26291 reward 2.53365 time 10000.0 params 455.192 0.315233 0.315233 reward 3.97048 time 10000.0 params 180.312 0.590804 0.590804 reward 3.53380 time 10000.0 params 180.312 0.590804 0.590804 reward 2.40003 time 10000.0 params 504.401 0.323131 0.323131 reward 4.64129 time 10000.0 params 429.426 0.371417 0.371417 reward 3.15497 time 10000.0 params 429.426 0.371417 0.371417 reward 5.21707 time 10000.0 params 350 0.5 0.5 reward 5.56549 time 10000.0 params 350 0.5 0.5 reward 2.59830 time 10000.0 params 350 0.5 0.5 reward 0.17376 time 10000.0 params 700 0 0 reward 1.09445 time 10000.0 params 690.506 0.0175886 0.0175886 reward -1.16487 time 10000.0 params 690.506 0.0175886 0.0175886 reward 4.15879 time 10000.0 params 230.081 0.672743 0.672743 reward -13.73013 time 10000.0 params 3.02778 0.241395 0.241395 reward -13.68507 time 10000.0 params 3.02778 0.241395 0.241395 reward -3.21566 time 10000.0 params 451.609 0.841651 0.841651 reward -3.33119 time 10000.0 params 28.8956 0.774371 0.774371 reward -3.29715 time 10000.0 params 28.8956 0.774371 0.774371 reward -2.38969 time 10000.0 params 386.871 1 1 reward -3.19417 time 10000.0 params 396.122 0.971439 0.971439 reward -6.02050 time 10000.0 params 396.122 0.971439 0.971439 reward -4.37008 time 10000.0 params 700 0.612768 0.612768 reward -3.94816 time 10000.0 params 690.605 0.618331 0.618331 reward -5.03817 time 10000.0 params 690.605 0.618331 0.618331 reward 2.25348 time 10000.0 params 429.491 0.432224 0.432224 reward 1.74343 time 10000.0 params 185.31 0.0135575 0.0135575 reward -0.27839 time 10000.0 params 185.31 0.0135575 0.0135575 reward 3.63748 time 10000.0 params 428.689 0.25096 0.25096 reward 1.71603 time 10000.0 params 641.582 0.300269 0.300269 reward 1.99134 time 10000.0 params 641.582 0.300269 0.300269 reward 4.67649 time 10000.0 params 373.5 0.300953 0.300953 reward 4.45610 time 10000.0 params 374.229 0.303913 0.303913 reward 3.79049 time 10000.0 params 374.229 0.303913 0.303913 reward 3.69934 time 10000.0 params 373.689 0.299821 0.299821 reward 2.54215 time 10000.0 params 514.202 0.169329 0.169329 reward 3.18027 time 10000.0 params 514.202 0.169329 0.169329 reward 4.29229 time 10000.0 params 374.567 0.298853 0.298853 reward -6.17205 time 10000.0 params 574.306 0.916686 0.916686 reward -7.47197 time 10000.0 params 574.306 0.916686 0.916686 reward 3.24452 time 10000.0 params 374.567 0.298853 0.298853 reward 2.25914 time 10000.0 params 216.474 0.830348 0.830348 reward 0.78958 time 10000.0 params 216.474 0.830348 0.830348 reward 4.44904 time 10000.0 params 390.499 0.288812 0.288812 reward 1.80192 time 10000.0 params 147.496 0.397951 0.397951 reward 1.20862 time 10000.0 params 147.496 0.397951 0.397951 reward 3.62538 time 10000.0 params 449.425 0.219538 0.219538 reward -2.20348 time 10000.0 params 384.923 0.758627 0.758627 reward -1.96277 time 10000.0 params 384.923 0.758627 0.758627 reward 4.68135 time 10000.0 params 374.229 0.303913 0.303913 reward 0.60388 time 10000.0 params 541.056 0.534235 0.534235 reward 2.22817 time 10000.0 params 541.056 0.534235 0.534235 reward 2.97890 time 10000.0 params 418.477 0.310072 0.310072 reward 1.34624 time 10000.0 params 85.0483 0.571037 0.571037 reward 1.53925 time 10000.0 params 85.0483 0.571037 0.571037 reward 5.32118 time 10000.0 params 381.985 0.37167 0.37167 reward 4.47410 time 10000.0 params 382.273 0.383307 0.383307 reward 4.01918 time 10000.0 params 382.273 0.383307 0.383307 reward 2.92916 time 10000.0 params 381.053 0.369391 0.369391 reward 3.74837 time 10000.0 params 378.916 0.359074 0.359074 reward 4.59004 time 10000.0 params 378.916 0.359074 0.359074 reward 4.50723 time 10000.0 params 399.741 0.295184 0.295184 reward 4.01418 time 10000.0 params 434.606 0.341957 0.341957 reward 4.47163 time 10000.0 params 434.606 0.341957 0.341957 reward 3.14848 time 10000.0 params 459.2 0.339394 0.339394 reward 4.85745 time 10000.0 params 467.428 0.352034 0.352034 reward 3.80674 time 10000.0 params 467.428 0.352034 0.352034 reward 4.86848 time 10000.0 params 397.781 0.292816 0.292816 reward 2.55573 time 10000.0 params 404.97 0.285458 0.285458 reward 2.38736 time 10000.0 params 404.97 0.285458 0.285458 reward 4.03037 time 10000.0 params 378.916 0.359074 0.359074 reward 3.92089 time 10000.0 params 601.294 0.236821 0.236821 reward 3.39374 time 10000.0 params 601.294 0.236821 0.236821 reward 3.53039 time 10000.0 params 378.916 0.359074 0.359074 reward 0.46149 time 10000.0 params 269.88 0.191627 0.191627 reward 1.34638 time 10000.0 params 269.88 0.191627 0.191627 reward 3.20489 time 10000.0 params 378.916 0.359074 0.359074 reward 3.77890 time 10000.0 params 216.817 0.515808 0.515808 reward 4.70238 time 10000.0 params 216.817 0.515808 0.515808 reward 3.83099 time 10000.0 params 378.916 0.359074 0.359074 reward 4.17391 time 10000.0 params 144.748 0.692278 0.692278 reward 3.78140 time 10000.0 params 144.748 0.692278 0.692278 reward 2.90675 time 10000.0 params 216.817 0.515808 0.515808 reward -5.85356 time 10000.0 params 19.7375 0.682447 0.682447 reward -5.89072 time 10000.0 params 19.7375 0.682447 0.682447 reward 3.78436 time 10000.0 params 216.817 0.515808 0.515808 reward -3.53827 time 10000.0 params 28.2459 0.748016 0.748016 reward -3.53176 time 10000.0 params 28.2459 0.748016 0.748016 reward 3.53936 time 10000.0 params 432.498 0.350089 0.350089 reward 0.21719 time 10000.0 params 392.846 0.0742435 0.0742435 reward -0.03880 time 10000.0 params 392.846 0.0742435 0.0742435 reward 3.95769 time 10000.0 params 382.273 0.383307 0.383307 reward 3.23306 time 10000.0 params 254.206 0.309644 0.309644 reward 2.69579 time 10000.0 params 254.206 0.309644 0.309644 reward 3.28260 time 10000.0 params 216.817 0.515808 0.515808 reward 0.83261 time 10000.0 params 65.0837 0.737202 0.737202 reward 1.03310 time 10000.0 params 65.0837 0.737202 0.737202 reward 2.82632 time 10000.0 params 216.817 0.515808 0.515808 reward 1.46810 time 10000.0 params 98.2893 0.670765 0.670765 reward 2.41931 time 10000.0 params 98.2893 0.670765 0.670765 reward 0.79255 time 10000.0 params 378.916 0.359074 0.359074 reward 4.97321 time 10000.0 params 584.658 0.247888 0.247888 reward 4.64447 time 10000.0 params 584.658 0.247888 0.247888 reward 5.10426 time 10000.0 params 378.916 0.359074 0.359074 reward 3.13343 time 10000.0 params 301.627 0.405722 0.405722 reward 5.17619 time 10000.0 params 301.627 0.405722 0.405722 reward 4.18750 time 10000.0 params 301.627 0.405722 0.405722 reward -0.05839 time 10000.0 params 49.8015 0.620341 0.620341 reward 0.11230 time 10000.0 params 49.8015 0.620341 0.620341 reward 4.67795 time 10000.0 params 301.627 0.405722 0.405722 reward 2.31601 time 10000.0 params 144.818 0.50453 0.50453 reward 2.84859 time 10000.0 params 144.818 0.50453 0.50453 reward 4.14455 time 10000.0 params 301.627 0.405722 0.405722 reward 3.69473 time 10000.0 params 209.13 0.484561 0.484561 reward 3.73250 time 10000.0 params 209.13 0.484561 0.484561 reward 2.96801 time 10000.0 params 378.916 0.359074 0.359074 reward 4.07935 time 10000.0 params 193.14 0.617469 0.617469 reward 3.52154 time 10000.0 params 193.14 0.617469 0.617469 reward 2.80842 time 10000.0 params 378.916 0.359074 0.359074 reward 3.10688 time 10000.0 params 563.424 0.158305 0.158305 reward 3.56719 time 10000.0 params 563.424 0.158305 0.158305 reward 1.70128 time 10000.0 params 378.916 0.359074 0.359074 reward 4.70274 time 10000.0 params 218.977 0.584531 0.584531 reward 3.85391 time 10000.0 params 218.977 0.584531 0.584531 reward 3.40677 time 10000.0 params 216.817 0.515808 0.515808 reward 2.39063 time 10000.0 params 684.323 0.110038 0.110038 reward 1.92413 time 10000.0 params 684.323 0.110038 0.110038 reward 4.16949 time 10000.0 params 350 0.5 0.5 reward 1.73661 time 10000.0 params 350 0.5 0.5 reward 3.62214 time 10000.0 params 350 0.5 0.5 reward 0.17980 time 10000.0 params 700 0 0 reward 0.10959 time 10000.0 params 688.254 0.00213839 0.00213839 reward 0.01320 time 10000.0 params 688.254 0.00213839 0.00213839 reward 5.13812 time 10000.0 params 229.282 0.667383 0.667383 reward -4.11915 time 10000.0 params 663.176 0.863829 0.863829 reward -5.08217 time 10000.0 params 663.176 0.863829 0.863829 reward 2.21680 time 10000.0 params 193.901 0.335886 0.335886 reward -4.36038 time 10000.0 params 24.6312 0.108301 0.108301 reward -4.35933 time 10000.0 params 24.6312 0.108301 0.108301 reward 2.32525 time 10000.0 params 340.324 0.471396 0.471396 reward -6.60946 time 10000.0 params 17.0742 0.743258 0.743258 reward -6.78113 time 10000.0 params 17.0742 0.743258 0.743258 reward 3.03051 time 10000.0 params 412.254 0.223271 0.223271 reward 0.90840 time 10000.0 params 378.662 0.0537578 0.0537578 reward -0.15330 time 10000.0 params 378.662 0.0537578 0.0537578 reward -2.25282 time 10000.0 params 688.787 0.367863 0.367863 reward -0.31289 time 10000.0 params 681.036 0.355047 0.355047 reward 3.12604 time 10000.0 params 681.036 0.355047 0.355047 reward 5.66121 time 10000.0 params 520.18 0.357616 0.357616 reward 3.16138 time 10000.0 params 185.928 0.469118 0.469118 reward 3.26708 time 10000.0 params 185.928 0.469118 0.469118 reward 3.38050 time 10000.0 params 430.34 0.414029 0.414029 reward -3.45224 time 10000.0 params 370.386 0.975554 0.975554 reward -4.02061 time 10000.0 params 370.386 0.975554 0.975554 reward 2.15680 time 10000.0 params 426.08 0.42253 0.42253 reward 2.30507 time 10000.0 params 423.473 0.41684 0.41684 reward 2.64856 time 10000.0 params 423.473 0.41684 0.41684 reward 2.62944 time 10000.0 params 406.207 0.431083 0.431083 reward 4.24296 time 10000.0 params 400.424 0.441665 0.441665 reward 0.84238 time 10000.0 params 400.424 0.441665 0.441665 reward 2.70177 time 10000.0 params 470.573 0.353804 0.353804 reward 3.41847 time 10000.0 params 402.546 0.255413 0.255413 reward 2.93719 time 10000.0 params 402.546 0.255413 0.255413 reward 4.02331 time 10000.0 params 350 0.5 0.5 reward 0.33410 time 10000.0 params 636.956 0.0466713 0.0466713 reward 0.09818 time 10000.0 params 636.956 0.0466713 0.0466713 reward 3.06454 time 10000.0 params 185.928 0.469118 0.469118 reward 3.83481 time 10000.0 params 165.766 0.867331 0.867331 reward 2.94269 time 10000.0 params 165.766 0.867331 0.867331 reward 3.57298 time 10000.0 params 185.928 0.469118 0.469118 reward 0.20139 time 10000.0 params 188.965 0.0549404 0.0549404 reward 0.42954 time 10000.0 params 188.965 0.0549404 0.0549404 reward -15.76135 time 10000.0 params 0 0.566039 0.566039 reward -7.62878 time 10000.0 params 14.6045 0.509267 0.509267 reward -7.67970 time 10000.0 params 14.6045 0.509267 0.509267 reward 3.56385 time 10000.0 params 185.928 0.469118 0.469118 reward 0.81870 time 10000.0 params 59.334 0.563695 0.563695 reward 0.45220 time 10000.0 params 59.334 0.563695 0.563695 reward 3.17166 time 10000.0 params 185.928 0.469118 0.469118 reward -2.81382 time 10000.0 params 421.063 0.925653 0.925653 reward -4.16293 time 10000.0 params 421.063 0.925653 0.925653 reward 3.51783 time 10000.0 params 185.928 0.469118 0.469118 reward -3.71834 time 10000.0 params 537.075 0.623271 0.623271 reward -0.05640 time 10000.0 params 537.075 0.623271 0.623271 reward 2.53460 time 10000.0 params 402.546 0.255413 0.255413 reward 1.88465 time 10000.0 params 257.207 0.240435 0.240435 reward 0.43179 time 10000.0 params 257.207 0.240435 0.240435 reward 3.82549 time 10000.0 params 402.546 0.255413 0.255413 reward 1.53632 time 10000.0 params 494.759 0.606899 0.606899 reward -2.49145 time 10000.0 params 494.759 0.606899 0.606899 reward 4.37116 time 10000.0 params 402.546 0.255413 0.255413 reward 1.78815 time 10000.0 params 195.295 0.333304 0.333304 reward 2.18727 time 10000.0 params 195.295 0.333304 0.333304 reward 4.62447 time 10000.0 params 408.493 0.325828 0.325828 reward 0.88598 time 10000.0 params 248.833 0.786129 0.786129 reward 2.47736 time 10000.0 params 248.833 0.786129 0.786129 reward 4.60965 time 10000.0 params 275.091 0.443729 0.443729 reward 3.18608 time 10000.0 params 193.334 0.626895 0.626895 reward 3.55581 time 10000.0 params 193.334 0.626895 0.626895 reward -0.27948 time 10000.0 params 248.833 0.786129 0.786129 reward 0.11680 time 10000.0 params 453.999 0.63695 0.63695 reward -1.70184 time 10000.0 params 453.999 0.63695 0.63695 reward 3.00582 time 10000.0 params 385.542 0.340003 0.340003 reward -1.34626 time 10000.0 params 39.0168 0.994516 0.994516 reward -1.87770 time 10000.0 params 39.0168 0.994516 0.994516 reward 3.19103 time 10000.0 params 193.334 0.626895 0.626895 reward -0.16590 time 10000.0 params 347.599 0.759561 0.759561 reward 1.06877 time 10000.0 params 347.599 0.759561 0.759561 reward 1.73756 time 10000.0 params 193.334 0.626895 0.626895 reward 4.62711 time 10000.0 params 567.212 0.20886 0.20886 reward 3.14039 time 10000.0 params 567.212 0.20886 0.20886 reward 4.10932 time 10000.0 params 394.17 0.334864 0.334864 reward 3.99786 time 10000.0 params 399.281 0.325867 0.325867 reward 3.49566 time 10000.0 params 399.281 0.325867 0.325867 reward 4.17067 time 10000.0 params 393.697 0.336838 0.336838 reward -3.92915 time 10000.0 params 643.288 0.559084 0.559084 reward -4.58069 time 10000.0 params 643.288 0.559084 0.559084 reward 3.18833 time 10000.0 params 119.779 0.674177 0.674177 reward 2.87747 time 10000.0 params 122.235 0.677065 0.677065 reward 3.23590 time 10000.0 params 122.235 0.677065 0.677065 reward 4.60680 time 10000.0 params 271.773 0.448546 0.448546 reward 3.26436 time 10000.0 params 271.752 0.448051 0.448051 reward 4.16419 time 10000.0 params 271.752 0.448051 0.448051 reward 3.63751 time 10000.0 params 270.398 0.451639 0.451639 reward 0.39069 time 10000.0 params 532.623 0.0333677 0.0333677 reward -0.65378 time 10000.0 params 532.623 0.0333677 0.0333677 reward 3.28612 time 10000.0 params 270.398 0.451639 0.451639 reward 2.71619 time 10000.0 params 307.5 0.318593 0.318593 reward 3.65479 time 10000.0 params 307.5 0.318593 0.318593 reward 3.25462 time 10000.0 params 285.656 0.467126 0.467126 reward 0.19720 time 10000.0 params 283.881 0.543086 0.543086 reward 1.87552 time 10000.0 params 283.881 0.543086 0.543086 reward 2.99809 time 10000.0 params 204.958 0.58087 0.58087 reward 3.02029 time 10000.0 params 199.516 0.58249 0.58249 reward 3.89564 time 10000.0 params 199.516 0.58249 0.58249 reward 4.37662 time 10000.0 params 247.627 0.469735 0.469735 reward 2.94769 time 10000.0 params 240.003 0.474434 0.474434 reward 3.38649 time 10000.0 params 240.003 0.474434 0.474434 reward 3.93153 time 10000.0 params 243.807 0.472437 0.472437 reward 4.77046 time 10000.0 params 244.332 0.471469 0.471469 reward 4.49830 time 10000.0 params 244.332 0.471469 0.471469 reward 4.02752 time 10000.0 params 246.254 0.470364 0.470364 reward 4.94056 time 10000.0 params 243.907 0.483407 0.483407 reward 4.09302 time 10000.0 params 243.907 0.483407 0.483407 reward 2.98792 time 10000.0 params 246.14 0.470424 0.470424 reward 4.44524 time 10000.0 params 240.693 0.438778 0.438778 reward 3.05133 time 10000.0 params 240.693 0.438778 0.438778 reward 2.06680 time 10000.0 params 350 0.5 0.5 reward 4.13819 time 10000.0 params 350 0.5 0.5 reward 1.61826 time 10000.0 params 350 0.5 0.5 reward 0.51620 time 10000.0 params 700 0 0 reward -0.25627 time 10000.0 params 693.507 0.0203527 0.0203527 reward 0.50320 time 10000.0 params 693.507 0.0203527 0.0203527 reward 4.23029 time 10000.0 params 231.128 0.673739 0.673739 reward 2.50959 time 10000.0 params 75.6117 0.986463 0.986463 reward 2.50405 time 10000.0 params 75.6117 0.986463 0.986463 reward -16.07954 time 10000.0 params 0 1 1 reward -3.34639 time 10000.0 params 665.158 0.973639 0.973639 reward -7.58293 time 10000.0 params 665.158 0.973639 0.973639 reward -16.29395 time 10000.0 params 0 0.756285 0.756285 reward -0.49129 time 10000.0 params 301.058 0.0199063 0.0199063 reward 0.26419 time 10000.0 params 301.058 0.0199063 0.0199063 reward -16.03326 time 10000.0 params 0 0.7976 0.7976 reward -0.59930 time 10000.0 params 44.7983 0.406288 0.406288 reward -0.55555 time 10000.0 params 44.7983 0.406288 0.406288 reward 0.13746 time 10000.0 params 48.878 1 1 reward -1.65607 time 10000.0 params 669.815 0.489911 0.489911 reward -2.88621 time 10000.0 params 669.815 0.489911 0.489911 reward 0.36587 time 10000.0 params 50.5273 1 1 reward 0.43788 time 10000.0 params 52.0984 0.976869 0.976869 reward 0.44017 time 10000.0 params 52.0984 0.976869 0.976869 reward 3.60569 time 10000.0 params 88.5892 1 1 reward 0.04889 time 10000.0 params 406.218 0.909758 0.909758 reward -0.13830 time 10000.0 params 406.218 0.909758 0.909758 reward 4.78649 time 10000.0 params 273.733 0.594365 0.594365 reward 2.45745 time 10000.0 params 272.273 0.600987 0.600987 reward 3.87249 time 10000.0 params 272.273 0.600987 0.600987 reward 3.81014 time 10000.0 params 315.605 0.503695 0.503695 reward -0.03360 time 10000.0 params 59.1501 0.0225216 0.0225216 reward 0.39960 time 10000.0 params 59.1501 0.0225216 0.0225216 reward 3.59202 time 10000.0 params 315.605 0.503695 0.503695 reward 3.02104 time 10000.0 params 493.09 0.176777 0.176777 reward 3.23783 time 10000.0 params 493.09 0.176777 0.176777 reward 4.08839 time 10000.0 params 332.42 0.467579 0.467579 reward -3.63359 time 10000.0 params 519.974 0.665232 0.665232 reward -0.69492 time 10000.0 params 519.974 0.665232 0.665232 reward 0.18759 time 10000.0 params 508.181 0 0 reward 0.12218 time 10000.0 params 505.89 0.0184339 0.0184339 reward -0.23847 time 10000.0 params 505.89 0.0184339 0.0184339 reward 4.06197 time 10000.0 params 350 0.5 0.5 reward 2.26038 time 10000.0 params 95.4625 0.692212 0.692212 reward 1.70795 time 10000.0 params 95.4625 0.692212 0.692212 reward 4.36489 time 10000.0 params 299.554 0.527985 0.527985 reward 3.13164 time 10000.0 params 231.132 0.767338 0.767338 reward 3.28230 time 10000.0 params 231.132 0.767338 0.767338 reward 3.35386 time 10000.0 params 272.273 0.600987 0.600987 reward 0.96658 time 10000.0 params 270.483 0.220331 0.220331 reward 1.27358 time 10000.0 params 270.483 0.220331 0.220331 reward 3.72601 time 10000.0 params 272.273 0.600987 0.600987 reward 1.52870 time 10000.0 params 458.508 0.160104 0.160104 reward 2.32999 time 10000.0 params 458.508 0.160104 0.160104 reward 3.99613 time 10000.0 params 272.273 0.600987 0.600987 reward 1.73056 time 10000.0 params 205.888 0.383609 0.383609 reward 3.04455 time 10000.0 params 205.888 0.383609 0.383609 reward 4.94147 time 10000.0 params 295.749 0.512085 0.512085 reward 3.40337 time 10000.0 params 150.743 0.563527 0.563527 reward 3.33698 time 10000.0 params 150.743 0.563527 0.563527 reward 1.80580 time 10000.0 params 344.772 0.56832 0.56832 reward 0.83458 time 10000.0 params 534.741 0.456742 0.456742 reward 1.44660 time 10000.0 params 534.741 0.456742 0.456742 reward 1.76836 time 10000.0 params 309.013 0.494638 0.494638 reward 1.77036 time 10000.0 params 310.795 0.508489 0.508489 reward 4.72231 time 10000.0 params 310.795 0.508489 0.508489 reward 4.09067 time 10000.0 params 288.462 0.467563 0.467563 reward 2.85634 time 10000.0 params 325.943 0.388412 0.388412 reward 4.72440 time 10000.0 params 325.943 0.388412 0.388412 reward 3.30511 time 10000.0 params 247.268 0.505376 0.505376 reward -0.63999 time 10000.0 params 395.107 0.0328366 0.0328366 reward -0.93040 time 10000.0 params 395.107 0.0328366 0.0328366 reward 3.85851 time 10000.0 params 247.268 0.505376 0.505376 reward 2.24493 time 10000.0 params 222.092 0.953857 0.953857 reward 0.82429 time 10000.0 params 222.092 0.953857 0.953857 reward 3.27743 time 10000.0 params 247.268 0.505376 0.505376 reward 4.03798 time 10000.0 params 252.631 0.505836 0.505836 reward 3.05750 time 10000.0 params 252.631 0.505836 0.505836 reward 2.24026 time 10000.0 params 310.795 0.508489 0.508489 reward 4.13914 time 10000.0 params 173.854 0.706256 0.706256 reward 3.70157 time 10000.0 params 173.854 0.706256 0.706256 reward 3.12564 time 10000.0 params 328.503 0.242597 0.242597 reward 1.94416 time 10000.0 params 328.172 0.229855 0.229855 reward 2.91382 time 10000.0 params 328.172 0.229855 0.229855 reward 2.95004 time 10000.0 params 310.795 0.508489 0.508489 reward 3.96658 time 10000.0 params 401.226 0.289072 0.289072 reward 3.86410 time 10000.0 params 401.226 0.289072 0.289072 reward 3.09114 time 10000.0 params 246.267 0.527368 0.527368 reward 5.10584 time 10000.0 params 203.924 0.61099 0.61099 reward 1.92964 time 10000.0 params 203.924 0.61099 0.61099 reward 2.86011 time 10000.0 params 325.943 0.388412 0.388412 reward 1.42939 time 10000.0 params 421.087 0.120959 0.120959 reward 1.12885 time 10000.0 params 421.087 0.120959 0.120959 reward 3.36999 time 10000.0 params 325.943 0.388412 0.388412 reward 5.05961 time 10000.0 params 140.184 0.851519 0.851519 reward 4.38865 time 10000.0 params 140.184 0.851519 0.851519 reward 4.41870 time 10000.0 params 325.943 0.388412 0.388412 reward 2.77362 time 10000.0 params 272.145 0.32587 0.32587 reward 3.07218 time 10000.0 params 272.145 0.32587 0.32587 reward 4.30205 time 10000.0 params 325.943 0.388412 0.388412 reward 1.45515 time 10000.0 params 421.357 0.146018 0.146018 reward 1.85552 time 10000.0 params 421.357 0.146018 0.146018 reward 5.33639 time 10000.0 params 325.943 0.388412 0.388412 reward 2.02949 time 10000.0 params 169.127 0.974119 0.974119 reward 3.60527 time 10000.0 params 169.127 0.974119 0.974119 reward 4.70162 time 10000.0 params 325.943 0.388412 0.388412 reward 2.92709 time 10000.0 params 394.586 0.235568 0.235568 reward 3.40839 time 10000.0 params 394.586 0.235568 0.235568 reward 2.63000 time 10000.0 params 264.485 0.560754 0.560754 reward 4.06779 time 10000.0 params 221.494 0.674723 0.674723 reward 2.54969 time 10000.0 params 221.494 0.674723 0.674723 reward 4.26864 time 10000.0 params 325.943 0.388412 0.388412 reward 1.30866 time 10000.0 params 379.482 0.150097 0.150097 reward 1.21034 time 10000.0 params 379.482 0.150097 0.150097 reward 3.92572 time 10000.0 params 325.943 0.388412 0.388412 reward 2.31040 time 10000.0 params 335.566 0.203812 0.203812 reward 1.61049 time 10000.0 params 335.566 0.203812 0.203812 reward 4.38568 time 10000.0 params 325.943 0.388412 0.388412 reward 3.64253 time 10000.0 params 326.167 0.543514 0.543514 reward 2.73043 time 10000.0 params 326.167 0.543514 0.543514 reward 4.43394 time 10000.0 params 350 0.5 0.5 reward 4.55749 time 10000.0 params 350 0.5 0.5 reward 2.18175 time 10000.0 params 350 0.5 0.5 reward -1.05110 time 10000.0 params 700 0 0 reward -0.12630 time 10000.0 params 684.525 0.0161621 0.0161621 reward -0.27489 time 10000.0 params 684.525 0.0161621 0.0161621 reward 3.92825 time 10000.0 params 227.936 0.672234 0.672234 reward 0.57753 time 10000.0 params 68.9528 0.0474381 0.0474381 reward 0.31600 time 10000.0 params 68.9528 0.0474381 0.0474381 reward 1.04150 time 10000.0 params 346.343 0.766578 0.766578 reward -3.56817 time 10000.0 params 691.164 0.858837 0.858837 reward -5.33990 time 10000.0 params 691.164 0.858837 0.858837 reward -15.86353 time 10000.0 params 0 1 1 reward -8.90639 time 10000.0 params 11.5704 0.988356 0.988356 reward -8.82602 time 10000.0 params 11.5704 0.988356 0.988356 reward -16.22382 time 10000.0 params 0 0.422644 0.422644 reward -14.19931 time 10000.0 params 2.14101 0.416379 0.416379 reward -14.27285 time 10000.0 params 2.14101 0.416379 0.416379 reward -2.24689 time 10000.0 params 364.228 0 0 reward -0.11439 time 10000.0 params 354.282 0.0134452 0.0134452 reward 0.35248 time 10000.0 params 354.282 0.0134452 0.0134452 reward 0.15718 time 10000.0 params 389.807 0 0 reward -0.48488 time 10000.0 params 615.924 0.412453 0.412453 reward 2.29888 time 10000.0 params 615.924 0.412453 0.412453 reward 0.06749 time 10000.0 params 420.017 0 0 reward 0.07479 time 10000.0 params 429.44 0.0280582 0.0280582 reward 0.63267 time 10000.0 params 429.44 0.0280582 0.0280582 reward 3.31802 time 10000.0 params 355.849 0.326772 0.326772 reward -2.77938 time 10000.0 params 397.252 0.954876 0.954876 reward 1.43320 time 10000.0 params 397.252 0.954876 0.954876 reward -0.94986 time 10000.0 params 421.835 0 0 reward 0.48410 time 10000.0 params 412.815 0.00498438 0.00498438 reward -0.21960 time 10000.0 params 412.815 0.00498438 0.00498438 reward -0.56430 time 10000.0 params 350 0.5 0.5 reward 5.57148 time 10000.0 params 172.681 0.795719 0.795719 reward 4.76330 time 10000.0 params 172.681 0.795719 0.795719 reward 2.16669 time 10000.0 params 354.456 0.422545 0.422545 reward 1.17744 time 10000.0 params 218.573 0.264871 0.264871 reward 1.37415 time 10000.0 params 218.573 0.264871 0.264871 reward 2.23671 time 10000.0 params 172.681 0.795719 0.795719 reward -0.08110 time 10000.0 params 47.6108 0.9348 0.9348 reward -0.18164 time 10000.0 params 47.6108 0.9348 0.9348 reward 2.17106 time 10000.0 params 358.664 0.57143 0.57143 reward -0.76780 time 10000.0 params 303.243 0.704939 0.704939 reward -0.17840 time 10000.0 params 303.243 0.704939 0.704939 reward 1.79368 time 10000.0 params 437.608 0.580374 0.580374 reward 0.35649 time 10000.0 params 447.913 0.593009 0.593009 reward -0.52575 time 10000.0 params 447.913 0.593009 0.593009 reward -16.07606 time 10000.0 params 0 0.603899 0.603899 reward -16.05666 time 10000.0 params 0.578777 0.604429 0.604429 reward -15.51987 time 10000.0 params 0.578777 0.604429 0.604429 reward -15.78200 time 10000.0 params 0 0.635889 0.635889 reward -0.93460 time 10000.0 params 42.3301 0.750138 0.750138 reward -0.78837 time 10000.0 params 42.3301 0.750138 0.750138 reward 0.49090 time 10000.0 params 403.854 0.55026 0.55026 reward 2.74742 time 10000.0 params 454.226 0.341907 0.341907 reward 0.30719 time 10000.0 params 454.226 0.341907 0.341907 reward 2.16113 time 10000.0 params 229.242 1 1 reward 0.96665 time 10000.0 params 228.91 0.993725 0.993725 reward 2.21599 time 10000.0 params 228.91 0.993725 0.993725 reward 5.09344 time 10000.0 params 200.713 0.667789 0.667789 reward 2.94660 time 10000.0 params 168.999 0.503446 0.503446 reward 2.70242 time 10000.0 params 168.999 0.503446 0.503446 reward 4.12927 time 10000.0 params 172.681 0.795719 0.795719 reward -0.18740 time 10000.0 params 442.784 0.633379 0.633379 reward -0.36549 time 10000.0 params 442.784 0.633379 0.633379 reward 2.24177 time 10000.0 params 172.681 0.795719 0.795719 reward 3.24212 time 10000.0 params 341.071 0.234754 0.234754 reward 2.64323 time 10000.0 params 341.071 0.234754 0.234754 reward 4.63514 time 10000.0 params 172.681 0.795719 0.795719 reward 0.42085 time 10000.0 params 149.728 0.146146 0.146146 reward 0.40880 time 10000.0 params 149.728 0.146146 0.146146 reward 5.08613 time 10000.0 params 172.681 0.795719 0.795719 reward 0.45924 time 10000.0 params 52.3557 0.981479 0.981479 reward 0.51619 time 10000.0 params 52.3557 0.981479 0.981479 reward 3.19571 time 10000.0 params 214.355 0.667134 0.667134 reward 4.63982 time 10000.0 params 205.726 0.678977 0.678977 reward 4.71742 time 10000.0 params 205.726 0.678977 0.678977 reward 3.35210 time 10000.0 params 214.373 0.667105 0.667105 reward 3.21488 time 10000.0 params 279.237 0.40032 0.40032 reward 2.83330 time 10000.0 params 279.237 0.40032 0.40032 reward 5.00220 time 10000.0 params 146.941 1 1 reward 3.52133 time 10000.0 params 152.445 0.988121 0.988121 reward 4.97688 time 10000.0 params 152.445 0.988121 0.988121 reward 3.72421 time 10000.0 params 166.172 0.907132 0.907132 reward 3.83879 time 10000.0 params 161.102 0.904112 0.904112 reward 3.88968 time 10000.0 params 161.102 0.904112 0.904112 reward 3.83198 time 10000.0 params 205.726 0.678977 0.678977 reward 4.21265 time 10000.0 params 288.702 0.748127 0.748127 reward 2.97614 time 10000.0 params 288.702 0.748127 0.748127 reward 2.24059 time 10000.0 params 134.436 1 1 reward 3.56064 time 10000.0 params 298.91 0.597783 0.597783 reward 3.28765 time 10000.0 params 298.91 0.597783 0.597783 reward 3.66230 time 10000.0 params 144.548 0.947145 0.947145 reward 3.93778 time 10000.0 params 136.777 0.946982 0.946982 reward 3.81990 time 10000.0 params 136.777 0.946982 0.946982 reward 4.97779 time 10000.0 params 201.777 0.853 0.853 reward 1.83404 time 10000.0 params 250.781 0.81877 0.81877 reward 2.17127 time 10000.0 params 250.781 0.81877 0.81877 reward 3.96800 time 10000.0 params 152.445 0.988121 0.988121 reward 3.47887 time 10000.0 params 149.802 0.640481 0.640481 reward 3.46428 time 10000.0 params 149.802 0.640481 0.640481 reward 4.48676 time 10000.0 params 152.445 0.988121 0.988121 reward 2.52929 time 10000.0 params 84.1787 0.862423 0.862423 reward 2.61434 time 10000.0 params 84.1787 0.862423 0.862423 reward 4.40636 time 10000.0 params 152.445 0.988121 0.988121 reward 1.84272 time 10000.0 params 274.166 0.361189 0.361189 reward 3.99990 time 10000.0 params 274.166 0.361189 0.361189 reward 2.76028 time 10000.0 params 172.681 0.795719 0.795719 reward 0.75608 time 10000.0 params 294.365 0.133361 0.133361 reward 1.07890 time 10000.0 params 294.365 0.133361 0.133361 reward 3.23811 time 10000.0 params 172.681 0.795719 0.795719 reward 3.38559 time 10000.0 params 211.597 0.535435 0.535435 reward 4.31219 time 10000.0 params 211.597 0.535435 0.535435 reward 2.84698 time 10000.0 params 181.459 0.760965 0.760965 reward 3.44935 time 10000.0 params 189.972 0.774613 0.774613 reward 3.39814 time 10000.0 params 189.972 0.774613 0.774613 reward 4.69739 time 10000.0 params 124.788 1 1 reward 1.74742 time 10000.0 params 165.261 0.396497 0.396497 reward 2.11404 time 10000.0 params 165.261 0.396497 0.396497 reward -0.52567 time 10000.0 params 349.601 0.855206 0.855206 reward -3.13659 time 10000.0 params 349.601 0.855206 0.855206