European Workshop on Reinforcement Learning (EWRL) is a (biennial) series of events that is being organized since 1994. To date, the sequential decision making problem with delayed rewards has been studied, under various guises, by various communities: machine learning, control, economics, applied mathematics, psychology and biology to name the foremost. EWRL'08, the eighth workshop in the series as well, aims to serve as a forum to discuss the current state-of-the-art and future research directions in this continuously growing field. We intend to make this an exciting event not only for the European RL community but also international researchers from related areas with many opportunities to share new knowledge and encourage collaborative work. We also hope to help the emergence of European projects in the 7th framework program that fall into the scope of RL.
EWRL'08 is planned to be a theme oriented event in which each main theme will be allocated a half-day session including (i) an overview or tutorial, (ii) technical contributions in the form of long and short papers, followed by (iii) discussions. There will be two special sessions; a general discussion session entitled "Where are we heading? - Current and Future Trends in RL", and a demonstration session entitled "Real-life Applications of RL".
Prof. Rich Sutton, University of Alberta, will also be our special guest.
Topics of interest include but not limited to:
* Exploration vs Exploitation Trade-off
* (Function) Approximation in RL
* Knowledge Representation in RL
* Theorical RL (Convergence and performance bounds, Complexity issues, Sensitivity analysis)
* Multi-Agent RL
* Regret-minimization Algorithms in Games
* Direct Policy Search and Policy Gradient Methods
* Reward design and inverse RL
* Bayesian vs Frequentist Approaches
* RL and Statistical Learning
* Metrics for Empirical Comparisons in RL
* Reducing RL to Inference, Regression and Classification
* RL to Sequence Prediction
* RL from Biological and Psychological Perspectives
Submission Deadline: April 10, 2008 (Extended)
Notification of Acceptance: May 10, 2008
Workshop: June 30 - July 3, 2008
(The week before ICML'08, COLT'08 and UAI'08 in Helsinki)
EWRL'08 is a FREE event, there won't be any registration fee. But, we kindly request you to complete a registration form for organizational purposes. Registration form will be online on April 1, 2008.
Limited travel grants are available to help fund travel and accommodation for (PhD) students. Interested students should visit our web site and fill-in the application form until April 30, 2008. Please contact us for more information.
* Paper: Papers should be prepared in LNCS format and should not exceed 14 pages. We also encourage short papers (4-6 pages) from students that present ongoing research. A poster may be designed alongside a presentation. Posters will be exhibited during the workshop so as to help people interactions.
After the workshop, a selection of papers will be published as a "Lecture Notes in Artificial Intelligence" volume by Springer. Papers submitted to other conferences can be submitted to EWRL'08, regardless of their acceptance in these conferences. However, only those that are copyright free are eligible for being published in the proceedings. We welcome papers that have been accepted to ICML 2008 (for presentation only); such papers are exempt from the reviewing process, and authors can submit either just the title, the abstract, or the article itself.
Please check out EWRL'08 web site for more information about submission.
* Tutorial: Please provide the title, speaker, abstract, and a plan/draft for the tutorial. An electronic version (pdf) of the presentation should be provided on the workshop website. It should be delivered at least a week beforehand.
* Demonstration: Please provide the title and abstract of your demonstration, as well as any multimedia document that can illustrate it.
The workshop will take place at IRCICA building, around the scientific campus of Lille, northern France.
Lille, the third largest metropolitan area in France, lies on the Brussels-Paris-London connection and is easily accessible by high-speed TGV trains or by plane. More information can be found at the web site of Lille Tourist office (http://www.lilletourism.com).
European Workshop on Reinforcement Learning 2008 organizing committee:
Manuel Loth, Sertan Girgin, Sebastien Bubeck, Remi Munos, Philippe Preux
@ team-project SequeL, INRIA
phone: +33 359 57 79 76