ICML Workshop

ICML Workshop on the Reinforcement Learning Competition 2013 (WRLCOMP) in conjunction with ICML 201316-21 June 2013 Atlanta, USA.

Submission Deadline: May 15, 2013 [Submission website]
(Extended to May 21, 2013)

Participate in the Competition

The competition is now open. Read instructions, and register your team to participate.

The competition will end after June 3rd.
Workshop program (June 21, 2013)
 9:00 -10:00  Introduction to the workshop, results, domains
10:00-10:30 Break
10:30-12:00 Presentations of approaches
13:30-14:30 Invited talk by Marc Deisenroth
14:30-15:30 Discussion on the future of the workshop.

Submit a paper

In the reinforcement learning competition, researchers can test their algorithms and insights in a friendly competitive way, on new and challenging domains. The reinforcement learning competition has not been organized for a while, but will take place again this year after a long hiatus. The primary aim of the competition is to test both general and domain-specific reinforcement learning algorithms, using an unbiased and transparent methodology. The domains used in the competition will form a set of benchmarks, and the results of the submitted algorithms will form a body of benchmark results, which researchers can then use as a basis of comparison in future work.

The ICML reinforcement learning competition workshop will bring together researchers, who participated in the competition, in order to present and discuss their results. We will evaluate what works, and also under what conditions established methods may not work so well. In this way we hope to broaden our insight into state-of-the-art RL algorithms, and important properties of RL problems. 

A secondary aim is to discuss methodological approaches for comparing reinforcement learning algorithms. This remains an issue in reinforcement learning in general.

Another important aim is to ensure the continuing existence of the competition, and the prevention of further hiatuses. Our aim is to ensure that the competition will organized annually again, from this year onward. To this extend we will try to build up an organization of interested researchers.

The domains will be available near the end of March - we will post a link to the domains and submission page on this website.

The preliminary planning
The workshop will be organized along the lines of the domains. One time slot will be reserved for each competition category winner. In addition, all competition entrants will be invited to submit a short paper describing their approach.

We will reserve a special time slot for papers on methodological problems that arise when comparing reinforcement learning algorithms.

We ask for papers (up to 4 pages) that describes the approach used in the competition, or findings and ideas that relate to research questions.
All papers submitted should be prepared according to ICML format, available here: http://icml.cc/2013/wp-content/uploads/2012/12/icml2013stylefiles.tar.gz
All papers must be submitted as PDF by May 21, 2013, and be made through Easychair at https://www.easychair.org/conferences/?conf=wrlcomp2013
Important Dates:
Submission Deadline: May 21, 2013
Author Notification: June 3, 2013
Competition End: June 3, 2012
Workshop: June 21, 2013

Acceptance criteria
The main criterion for acceptance will be a rigorous analysis of the factors that contributed to an entry's success or failure. Secondary criteria will be novelty and performance.
Finally, we will also welcome papers on methodological problems that arise when comparing reinforcement learning algorithms.


Program Committee

  • Mauricio Araya
  • Olivier Buffet
  • Marc Deisenroth
  • Christos Dimitrakakis
  • Guangliang Li
  • Diederik Roijers
  • Ronald Ortner
  • Vincent Thomas
  • Nikolaos Tziortziotis
  • Nikos Vlassis