Recent Advances in Reinforcement Learning -

. .

Résumé :
Inthesummerof2008,reinforcementlearningresearchersfromaroundtheworld gathered in the north of France for a week of talks and discussions on reinfor- ment learning, on how it could be made more e?cient, applied to a broader range of applications, and utilized at more abstract and symbolic levels. As a participant in this 8th European Workshop on Reinforcement Learning, I was struck by both the quality and quantity of the presentations. There were four full days of short talks, over 50 in all, far more than there have been at any p- vious meeting on reinforcement learning in Europe, or indeed, anywhere else in the world. There was an air of excitement as substantial progress was reported in many areas including Computer Go, robotics, and ?tted methods. Overall, the work reported seemed to me to be an excellent, broad, and representative sample of cutting-edge reinforcement learning research. Some of the best of it is collected and published in this volume. The workshopandthe paperscollectedhere provideevidence thatthe ?eldof reinforcement learning remains vigorous and varied. It is appropriate to re?ect on some of the reasons for this. One is that the ?eld remains focused on a pr- lem ? sequential decision making ? without prejudice as to solution methods. Another is the existence of a common terminology and body of theory.

Sommaire:
Lazy Planning under Uncertainty by Optimizing Decisions on an Ensemble of Incomplete Disturbance Trees.- Exploiting Additive Structure in Factored MDPs for Reinforcement Learning.- Algorithms and Bounds for Rollout Sampling Approximate Policy Iteration.- Efficient Reinforcement Learning in Parameterized Models: Discrete Parameter Case.- Regularized Fitted Q-Iteration: Application to Planning.- A Near Optimal Policy for Channel Allocation in Cognitive Radio.- Evaluation of Batch-Mode Reinforcement Learning Methods for Solving DEC-MDPs with Changing Action Sets.- Bayesian Reward Filtering.- Basis Expansion in Natural Actor Critic Methods.- Reinforcement Learning with the Use of Costly Features.- Variable Metric Reinforcement Learning Methods Applied to the Noisy Mountain Car Problem.- Optimistic Planning of Deterministic Systems.- Policy Iteration for Learning an Exercise Policy for American Options.- Tile Coding Based on Hyperplane Tiles.- Use of Reinforcement Learning in Two Real Applications.- Applications of Reinforcement Learning to Structured Prediction.- Policy Learning - A Unified Perspective with Applications in Robotics.- Probabilistic Inference for Fast Learning in Control.- United We Stand: Population Based Methods for Solving Unknown POMDPs.- New Error Bounds for Approximations from Projected Linear Equations.- Markov Decision Processes with Arbitrary Reward Processes.