Welcome to the official website for the Second Annual Reinforcement Learning Competition. Building on last year's competition and the benchmarking events that preceded it, this event will be a forum for reinforcement learning researchers to rigorously compare the performance of their methods on a suite of challenging domains.

These problems will be significantly more complex and difficult than those used in previous years. They include: the game of Tetris; robot soccer keepaway, based on the RoboCup simulator; a real-time strategy (RTS) game; and a helicopter control problem, based on the work of Andrew Ng and collaborators.  See the Domains Page for more details on competition events.

Prizes will be awarded to the winners of each event!  Details have not been finalized yet, but these prizes will include things like Nintendo Wiis, iPod Touches, Xbox 360s, etc.  Depending on fundraising still in progress, prizes for second and third place may also be awarded.

This year's competition will utilize new evaluation paradigms designed to encourage algorithms that generalize well to previously unseen tasks. In particular, each domain will be parameterized and test parameters will differ from those used for training.  As a result, only learning algorithms that are robust across a range of parameters can expect to perform well.  Algorithms will be compared based on cumulative reward achieved while interacting with the competition domains (online learning). See the Rules Page for more details on these evaluation paradigms.

Test runs begin on June 1st and the competition will conclude with a workshop at ICML-08 on July 9th in Helsinki, Finland, where the winners will be announced.  All competitors are invited to participate in a poster session at the workshop. The workshop will also feature discussions about the challenges of empirical AI and the future of the competition. Note that regular registration for ICML-08 ends on June 18th.

Please peruse this web site to learn more about the format of the competition and domains it will include.

Please direct all questions to the Discussion Page.

RL-Competition Button and Poster

Put this button on your home page with the following code:

<a href=http://rl-competition.org><img border=0 src="http://rl-competition.org/images/stories/participantbutton.png"></a> 

 Also, please download and print the RL-Competition poster and put it up in your department!

 Previous, related workshops

• 2006 NIPS Workshop: First Annual Reinforcement Learning Competition
• 2006 ICML Workshop: Reinforcement Learning Competition and Benchmarking Event
• 2005 NIPS Workshop: Reinforcement Learning Benchmarks and Bake-offs II
• 2004 NIPS Workshop: Reinforcement Learning Benchmarks and Bake-offs