Recent Advances in Reinforcement Learning: 8th European Workshop, EWRL 2008, Villeneuve d’Ascq, France, June 30-July 3, 2008, Revised and Selected Papers

Front Matter....Pages -
Lazy Planning under Uncertainty by Optimizing Decisions on an Ensemble of Incomplete Disturbance Trees....Pages 1-14
Exploiting Additive Structure in Factored MDPs for Reinforcement Learning....Pages 15-26
Algorithms and Bounds for Rollout Sampling Approximate Policy Iteration....Pages 27-40
Efficient Reinforcement Learning in Parameterized Models: Discrete Parameter Case....Pages 41-54
Regularized Fitted Q-Iteration: Application to Planning....Pages 55-68
A Near Optimal Policy for Channel Allocation in Cognitive Radio....Pages 69-81
Evaluation of Batch-Mode Reinforcement Learning Methods for Solving DEC-MDPs with Changing Action Sets....Pages 82-95
Bayesian Reward Filtering....Pages 96-109
Basis Expansion in Natural Actor Critic Methods....Pages 110-123
Reinforcement Learning with the Use of Costly Features....Pages 124-135
Variable Metric Reinforcement Learning Methods Applied to the Noisy Mountain Car Problem....Pages 136-150
Optimistic Planning of Deterministic Systems....Pages 151-164
Policy Iteration for Learning an Exercise Policy for American Options....Pages 165-178
Tile Coding Based on Hyperplane Tiles....Pages 179-190
Use of Reinforcement Learning in Two Real Applications....Pages 191-204
Applications of Reinforcement Learning to Structured Prediction....Pages 205-219
Policy Learning – A Unified Perspective with Applications in Robotics....Pages 220-228
Probabilistic Inference for Fast Learning in Control....Pages 229-242
United We Stand: Population Based Methods for Solving Unknown POMDPs....Pages 243-252
New Error Bounds for Approximations from Projected Linear Equations....Pages 253-267
Markov Decision Processes with Arbitrary Reward Processes....Pages 268-281
Back Matter....Pages -