Recent Advances in Reinforcement Learning: 9th European Workshop, EWRL 2011, Athens, Greece, September 9-11, 2011, Revised Selected Papers

Front Matter....Pages -
Invited Talk: UCRL and Autonomous Exploration....Pages 1-1
Invited Talk: Increasing Representational Power and Scaling Inference in Reinforcement Learning....Pages 2-2
Invited Talk: PRISM – Practical RL: Representation, Interaction, Synthesis, and Mortality....Pages 3-3
Invited Talk: Towards Robust Reinforcement Learning Algorithms....Pages 4-4
Automatic Discovery of Ranking Formulas for Playing with Multi-armed Bandits....Pages 5-17
Goal-Directed Online Learning of Predictive Models....Pages 18-29
Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Control....Pages 30-41
Active Learning of MDP Models....Pages 42-53
Handling Ambiguous Effects in Action Learning....Pages 54-65
Feature Reinforcement Learning in Practice....Pages 66-77
Reinforcement Learning with a Bilinear Q Function....Pages 78-88
ℓ 1 -Penalized Projected Bellman Residual....Pages 89-101
Regularized Least Squares Temporal Difference Learning with Nested ℓ 2 and ℓ 1 Penalization....Pages 102-114
Recursive Least-Squares Learning with Eligibility Traces....Pages 115-127
Value Function Approximation through Sparse Bayesian Modeling....Pages 128-139
Automatic Construction of Temporally Extended Actions for MDPs Using Bisimulation Metrics....Pages 140-152
Unified Inter and Intra Options Learning Using Policy Gradient Methods....Pages 153-164
Options with Exceptions....Pages 165-176
Robust Bayesian Reinforcement Learning through Tight Lower Bounds....Pages 177-188
Optimized Look-ahead Tree Search Policies....Pages 189-200
A Framework for Computing Bounds for the Return of a Policy....Pages 201-212
Transferring Evolved Reservoir Features in Reinforcement Learning Tasks....Pages 213-224
Transfer Learning via Multiple Inter-task Mappings....Pages 225-236
Multi-Task Reinforcement Learning: Shaping and Feature Selection....Pages 237-248
Transfer Learning in Multi-Agent Reinforcement Learning Domains....Pages 249-260
An Extension of a Hierarchical Reinforcement Learning Algorithm for Multiagent Settings....Pages 261-272
Bayesian Multitask Inverse Reinforcement Learning....Pages 273-284
Batch, Off-Policy and Model-Free Apprenticeship Learning....Pages 285-296
Introduction of Fixed Mode States into Online Profit Sharing and Its Application to Waist Trajectory Generation of Biped Robot....Pages 297-308
MapReduce for Parallel Reinforcement Learning....Pages 309-320
Compound Reinforcement Learning: Theory and an Application to Finance....Pages 321-332
Proposal and Evaluation of the Active Course Classification Support System with Exploitation-Oriented Learning....Pages 333-344
Back Matter....Pages -