Skip to main content
  • Conference proceedings
  • © 2008

Recent Advances in Reinforcement Learning

8th European Workshop, EWRL 2008, Villeneuve d'Ascq, France, June 30-July 3, 2008, Revised and Selected Papers

Part of the book series: Lecture Notes in Computer Science (LNCS, volume 5323)

Part of the book sub series: Lecture Notes in Artificial Intelligence (LNAI)

Conference series link(s): EWRL: European Workshop on Reinforcement Learning

Conference proceedings info: EWRL 2008.

Buying options

eBook USD 39.99
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 54.99
Price excludes VAT (Canada)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions

This is a preview of subscription content, access via your institution.

Table of contents (21 papers)

  1. Front Matter

  2. Exploiting Additive Structure in Factored MDPs for Reinforcement Learning

    • Thomas Degris, Olivier Sigaud, Pierre-Henri Wuillemin
    Pages 15-26
  3. Algorithms and Bounds for Rollout Sampling Approximate Policy Iteration

    • Christos Dimitrakakis, Michail G. Lagoudakis
    Pages 27-40
  4. Efficient Reinforcement Learning in Parameterized Models: Discrete Parameter Case

    • Kirill Dyagilev, Shie Mannor, Nahum Shimkin
    Pages 41-54
  5. Regularized Fitted Q-Iteration: Application to Planning

    • Amir massoud Farahmand, Mohammad Ghavamzadeh, Csaba Szepesvári, Shie Mannor
    Pages 55-68
  6. A Near Optimal Policy for Channel Allocation in Cognitive Radio

    • Sarah Filippi, Olivier Cappé, Fabrice Clérot, Eric Moulines
    Pages 69-81
  7. Bayesian Reward Filtering

    • Matthieu Geist, Olivier Pietquin, Gabriel Fricout
    Pages 96-109
  8. Basis Expansion in Natural Actor Critic Methods

    • Sertan Girgin, Philippe Preux
    Pages 110-123
  9. Reinforcement Learning with the Use of Costly Features

    • Robby Goetschalckx, Scott Sanner, Kurt Driessens
    Pages 124-135
  10. Optimistic Planning of Deterministic Systems

    • Jean-François Hren, Rémi Munos
    Pages 151-164
  11. Tile Coding Based on Hyperplane Tiles

    • Daniele Loiacono, Pier Luca Lanzi
    Pages 179-190
  12. Use of Reinforcement Learning in Two Real Applications

    • José D. Martín-Guerrero, Emilio Soria-Olivas, Marcelino Martínez-Sober, Antonio J. Serrrano-López, Rafael Magdalena-Benedito, Juan Gómez-Sanchis
    Pages 191-204
  13. Applications of Reinforcement Learning to Structured Prediction

    • Francis Maes, Ludovic Denoyer, Patrick Gallinari
    Pages 205-219
  14. Policy Learning – A Unified Perspective with Applications in Robotics

    • Jan Peters, Jens Kober, Duy Nguyen-Tuong
    Pages 220-228
  15. Probabilistic Inference for Fast Learning in Control

    • Carl Edward Rasmussen, Marc Peter Deisenroth
    Pages 229-242

Other Volumes

  1. Recent Advances in Reinforcement Learning

About this book

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.

Keywords

  • Bayesian filtering
  • algorithmic learning
  • classification
  • decision making
  • dynamic programming
  • ensemble methods
  • evolutionary systems
  • learning
  • machine learning
  • neural networks
  • optimal sampling
  • optimistic decision making
  • planning
  • poli
  • reinforcement learning

Editors and Affiliations

  • INRIA Lille-Nord Europe, Villeneuve d’Ascq, France

    Sertan Girgin

  • INRIA, LIFL, CNRS, Université de Lille, Villeneuve d’Ascq, France

    Manuel Loth, Rémi Munos, Philippe Preux, Daniil Ryabko

Bibliographic Information

Buying options

eBook USD 39.99
Price excludes VAT (Canada)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book USD 54.99
Price excludes VAT (Canada)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Learn about institutional subscriptions