Recent Advances in Reinforcement Learning

9th European Workshop, EWRL 2011, Athens, Greece, September 9-11, 2011, Revised Selected Papers

Editors:

ISBN: 978-3-642-29945-2 (Print) 978-3-642-29946-9 (Online)

Table of contents (32 chapters)

previous Page of 2
  1. Front Matter

    Pages -

  2. Invited Talk Abstracts

    1. No Access

      Book Chapter

      Pages 1-1

      Invited Talk: UCRL and Autonomous Exploration

    2. No Access

      Book Chapter

      Pages 2-2

      Invited Talk: Increasing Representational Power and Scaling Inference in Reinforcement Learning

    3. No Access

      Book Chapter

      Pages 3-3

      Invited Talk: PRISM – Practical RL: Representation, Interaction, Synthesis, and Mortality

    4. No Access

      Book Chapter

      Pages 4-4

      Invited Talk: Towards Robust Reinforcement Learning Algorithms

  3. Online Reinforcement Learning

    1. No Access

      Book Chapter

      Pages 5-17

      Automatic Discovery of Ranking Formulas for Playing with Multi-armed Bandits

    2. No Access

      Book Chapter

      Pages 18-29

      Goal-Directed Online Learning of Predictive Models

    3. No Access

      Book Chapter

      Pages 30-41

      Gradient Based Algorithms with Loss Functions and Kernels for Improved On-Policy Control

  4. Learning and Exploring MDPs

    1. No Access

      Book Chapter

      Pages 42-53

      Active Learning of MDP Models

    2. No Access

      Book Chapter

      Pages 54-65

      Handling Ambiguous Effects in Action Learning

    3. No Access

      Book Chapter

      Pages 66-77

      Feature Reinforcement Learning in Practice

  5. Function Approximation Methods for Reinforcement Learning

    1. No Access

      Book Chapter

      Pages 78-88

      Reinforcement Learning with a Bilinear Q Function

    2. No Access

      Book Chapter

      Pages 89-101

      1-Penalized Projected Bellman Residual

    3. No Access

      Book Chapter

      Pages 102-114

      Regularized Least Squares Temporal Difference Learning with Nested ℓ2 and ℓ1 Penalization

    4. No Access

      Book Chapter

      Pages 115-127

      Recursive Least-Squares Learning with Eligibility Traces

    5. No Access

      Book Chapter

      Pages 128-139

      Value Function Approximation through Sparse Bayesian Modeling

  6. Macro-actions in Reinforcement Learning

    1. No Access

      Book Chapter

      Pages 140-152

      Automatic Construction of Temporally Extended Actions for MDPs Using Bisimulation Metrics

    2. No Access

      Book Chapter

      Pages 153-164

      Unified Inter and Intra Options Learning Using Policy Gradient Methods

    3. No Access

      Book Chapter

      Pages 165-176

      Options with Exceptions

  7. Policy Search and Bounds

    1. No Access

      Book Chapter

      Pages 177-188

      Robust Bayesian Reinforcement Learning through Tight Lower Bounds

    2. No Access

      Book Chapter

      Pages 189-200

      Optimized Look-ahead Tree Search Policies

previous Page of 2