Table of Contents

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.