Proceedings of the 1994 Workshop on Robot Learning

To be held July 10, 1994, as part of the 1994 International Conference on Machine Learning

Workshop schedule.

Workshop chair: Sridhar Mahadevan (

Table of Contents:

Following are many of the papers that will appear in the workshop proceedings. This list is growing as authors provide URLs for their papers, so check in again soon for updates.

  • "Purposive Behavior Acquisition On a Real Robot By A Vision-Based Reinforcement Learning" Asada, M., Noda, S., Tawaratsunida, S. and Hosoda, K.
  • "Learning Control Functions for Industrial Robots," Baroglio, C., Giordana, A., and Piola, R. (retrieve the abstract only.)
  • "An Intelligent Agent Architecture In Which to Pursue Robot Learning," Bonasso, R. P., and Kortenkamp, D. (retrieve the abstract only.)
  • "Neural Network Robot Learning Mechanisms for Maneuvering in a Workspace," de Vel, O., and Milward, R.
  • "The Role of the Trainer in Reinforcement Learning" Dorigo, M., and Colombetti, M.
  • "(not yet accessible)" Facchinetti, C.
  • "An Evolutionary Approach to Learning in Robots," Grefenstette J., and Schultz, A. (retrieve the abstract only.)
  • "A Neural Network Pole Balancer that Learns and Operates on a Real Robot in Real Time" Hougen, D., Fischer, J., and Johnam, D.
  • "Incorporating Advice into Agents that Learn from Reinforcements," Maclin, R., and Shavlik, J. (retrieve the abstract only.)
  • "Reduced Training Time for Reinforcement Learning with Hidden State," McCallum, R. A. (retrieve the abstract only.)
  • "First Results with Instance-Based State Identification for Reinforcement Learning" McCallum, R. A.
  • "Explanation-Based Learning for Mobile Robot Perception," Mitchell, T., O'Sullivan, J., and Thrun S. (retrieve the abstract only.)
  • "The CMU Learning Robot Laboratory Data Toolkit," O'Sullivan, J. (retrieve the abstract only.)
  • "How an Embedded Agent can Infer the Structure of a Continuous World," Pierce, D. and Kuipers, B, (a one-page summary of the AAAI-94 paper "Learning to Explore and Build Maps." )
  • "Active Exploration Based ID-3 Based Learning for Robot Grasping," Salganicoff, M., Kunin, L. G., and Ungar, L. H.
  • "Learning Decision Trees for Mapping the Local Environment in Mobile Robot Navigation," Sillitoe, I., and Elomaa, T.
  • "Discounting Considered Harmful: A Comparision of Reinforcement Learning Methods for Automatic Guided Vehicle Scheduling" Tadepalli, P., and Ok, D. (retrieve the abstract only.)
  • "A Modular Q-Learning Architecture for Manipulator Task Decomposition," Tham, C. K., and Prager, R. W. (retrieve the abstract only.)