Robotics Institute
Carnegie Mellon University
Stéphane Ross
Stéphane Ross
Office: Smith Hall 201
Phone: 412-268-9515
Email: stephaneross at cmu dot edu
Refereed Journal Papers
  • A Bayesian Approach for Learning and Planning in Partially Observable Markov Decision Processes. [pdf]
    S. Ross, J. Pineau, B. Chaib-draa & P. Kreitmann
    In Journal of Machine Learning Research (JMLR), vol. 12, p. 1729-1770, 2011.
  • Online Planning Algorithms for POMDPs. [pdf]
    S. Ross, J. Pineau, S. Paquet & B. Chaib-draa
    In Journal of Artificial Intelligence Research (JAIR), vol. 32, p. 663-704, 2008.
Refereed Conference Papers
  • Normalized Online Learning. [pdf]
    S. Ross, P. Mineiro & J. Langford
    In Proceedings of the 29th Conference on Uncertainty in Artificial Intelligenc (UAI), 2013.
  • Learning Policies for Contextual Submodular Prediction. [pdf] [proofs (pdf)]
    S. Ross, J. Zhou, Y. Yue, D. Dey & J. A. Bagnell
    In Proceedings of the 30th International Conference on Machine Learning (ICML), 2013.
  • Learning Monocular Reactive UAV Control in Cluttered Natural Environments. [arXiv]
    S. Ross, N. Melik-Barkhudarov, K. S. Shankar, A. Wendel, D. Dey, J. A. Bagnell & M. Hebert
    In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2013.
  • Agnostic System Identification for Model-Based Reinforcement Learning. [pdf] [supplementary material (pdf)] [talk]
    S. Ross & J. A. Bagnell.
    In Proceedings of the 29th International Conference on Machine Learning (ICML), 2012.
  • Learning Message-Passing Inference Machines for Structured Prediction. [pdf] [poster (pdf)]
    S. Ross, D. Munoz, M. Hebert & J. A. Bagnell.
    In Proceedings of the 24th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2011.
  • A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning. [pdf] [slides (pdf)] [talk]
    S. Ross, G. J. Gordon & J. A. Bagnell.
    In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), 2011.
  • Efficient Reductions for Imitation Learning. [pdf] [supplementary material (pdf)]
    S. Ross & J. A. Bagnell.
    In Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), 2010.
  • Sensitivity Analysis of POMDP Value Functions. [pdf]
    S. Ross, M. Izadi, M. Mercer & D. Buckeridge.
    In Proceedings of the 8th International Conference on Machine Learning and Applications (ICMLA), 2009.
  • Bayesian Reinforcement Learning in POMDPs with Gaussian Processes. [pdf]
    P. Dallaire, C. Besse, S. Ross & B. Chaib-draa.
    In Proceedings of the International Conference on Intelligent Robots and Systems (IROS), 2009.
  • Model-Based Bayesian Reinforcement Learning in Large Structured Domains. [pdf]
    S. Ross & J. Pineau.
    In Proceedings of the 24th Conference on Uncertainty in Artificial Intelligence (UAI), 2008.
  • Bayesian Reinforcement Learning in Continuous POMDPs with Application to Robot Navigation. [pdf] [slides (pdf)]
    S. Ross, B. Chaib-draa & J. Pineau.
    In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2008.
  • Bayes-Adaptive POMDPs. [pdf] [Proofs (pdf)]
    S. Ross, B. Chaib-draa & J. Pineau.
    In Advances in Neural Information Processing Systems 20 (NIPS), 2008.
  • Theoretical Analysis of Heuristic Search Methods for Online POMDPs. [pdf]
    S. Ross, J. Pineau & B. Chaib-draa.
    In Advances in Neural Information Processing Systems 20 (NIPS), 2008.
  • AEMS : An Anytime Online Search Algorithm for Approximate Policy Refinement in Large POMDPs. [pdf]
    S. Ross & B. Chaib-draa.
    In Proceedings of the 20th International Joint Conference on Artificial Intelligence (IJCAI), 2007.
  • Satisfaction Equilibrium : Achieving Cooperation in Incomplete Information Games. [pdf] [slides (ppt)]
    S. Ross & B. Chaib-draa.
    In Proceedings of the 19th Canadian Conference on Artificial Intelligence (CanAI), 2006.
Refereed Workshop Papers
  • Bayes-Adaptive POMDPs: A New Perspective on the Explore-Exploit Tradeoff in Partially Observable Domains. [pdf]
    J. Pineau, S. Ross & B. Chaib-draa.
    In Proceedings of the 10th Symposium on Artificial Intelligence and Mathematics (ISAIM), 2008.
  • Online Policy Improvement in Large POMDPs via an Error Minimization Search. [pdf] [slides (pdf)]
    S. Ross, J. Pineau & B. Chaib-draa.
    In Proceedings of the 2nd North East Student Colloquium on Artificial Intelligence (NESCAI), 2007.
  • Learning to Play a Satisfaction Equilibrium. [pdf]
    S. Ross & B. Chaib-draa.
    In Proceedings of the Workshop on Evolutionary Models of Collaboration (EMC), 2007.
  • Hybrid POMDP Algorithms. [pdf]
    S. Paquet, B. Chaib-draa & S. Ross.
    In Proceedings of The Workshop on Multi-Agent Sequential Decision Making in Uncertain Domains (MSDM), 2006.
Technical Reports
  • Learning Monocular Reactive UAV Control in Cluttered Natural Environments. [arXiv]
    S. Ross, N. Melik-Barkhudarov, K. S. Shankar, A. Wendel, D. Dey, J. A. Bagnell & M. Hebert
    ArXiv 1211.1690, 2012.
  • Agnostic System Identification for Model-Based Reinforcement Learning. [arXiv]
    S. Ross & J. A. Bagnell.
    ArXiv 1203.1007, 2012.
  • Stability Conditions for Online Learnability. [arXiv]
    S. Ross & J. A. Bagnell.
    ArXiv 1108.3154, 2011.
  • Bayes-Adaptive POMDPs. [pdf]
    S. Ross, B. Chaib-draa & J. Pineau.
    Technical Report SOCS-TR-2007.6. McGill University, 2007. (Longer version of the similarly titled NIPS paper).
  • Report on Satisfaction Equilibria. [pdf]
    S. Ross & B. Chaib-draa.
    2006.
Thesis
  • Interactive Learning for Sequential Decisions and Predictions. [pdf]
    S. Ross.
    Ph.D. Thesis, Carnegie Mellon University, 2013.
  • Model-Based Bayesian Reinforcement Learning in Complex Domains. [pdf]
    S. Ross.
    M.Sc. Thesis, McGill University, 2008.

Welcome | Research | Publications | C.V. | Links

Author: Stéphane Ross
Email: stephaneross at cmu dot edu

This website is best viewed in 800x600 or higher resolution.