Connectionists: NIPS*06 Workshop: First Annual Reinforcement Learning Competition

[Adam White]

          NIPS*06 Workshop - Whistler, BC, December 9, 2006

                        "First Annual Reinforcement Learning  
Competition"

======================================================

http://rlai.cs.ualberta.ca/RLAI/rlc.html

----------------------------
Call for participation
----------------------------

Teams can compete in 7 events:

-  Cat and Mouse
-  Tetris
-  Garnet
-  Non-stationary Mountain Car
-  Cart-pole
-  Puddle World

The winners of the six individual events will be invited to give  
short talks, at the workshop, outlining their solution techniques.  
Each team is also encouraged to submitt a two page description of  
their solution techniques for each event they compete in. Teams are  
required to register their team with Adam White  
(awhite at cs.ualberta.ca). See the workshop web-page for a compete  
description of the problems, evaluation scheme and rules.

A pentathlon event will be announced in a few days. Look for the  
announcement and description of the pentathlon on the workshop web- 
page. In the Pentathlon each participant's agent will be evaluated on  
five continuous observation problems consecutively. The agents that  
perform best across all five problems will be awarded small prizes.


------------------------
Important Dates
------------------------

Initial software release and official start of competition:  October  
26, 2006

Competition end: December 3, 2006

Submission deadline for Solution descriptions: December 5, 2006

The server will come online a few days after the initial software has  
been released. Participants are encouraged to begin writing agents  
and testing locally before connecting to the competition server.


---------------------------------------------------
Workshop Description and Motivation
---------------------------------------------------

Competitions can greatly increase the interest and focus in an area  
by clarifying its objectives and challenges, publicly acknowledging  
the best algorithms, and generally making the area more exciting and  
enjoyable. The First Annual Reinforcement Learning competition is  
ongoing and will reach culmination six days before this workshop  
(December 3rd). The purpose of this one day workshop is to 1) report  
the results from the competition, 2) summarize the experiences of and  
solution approaches employed by the competition participants, and 3)  
plan for future competitions.

There have been two previous events within the machine learning  
community that have involved comparing different reinforcement  
learning methods, one at a NIPS 2005 workshop and one at a ICML 2006  
workshop. Last year's event at NIPS had over 30 submissions, from 9  
countries. This competition differs from previous events in that it  
will be a competitive event. The winners will be invited to describe  
their approach to each problem, at the workshop, improving the  
attendees’ expertise on applying and implementing reinforcement  
learning systems. This year's competition will feature seven events,  
three discrete observation problems and three continuous observation  
problems. The final event will be a Pentathlon: each participant's  
agent will be evaluated on five continuous observation problems  
consecutively. The agents that perform best across all five problems  
will be awarded small prizes.


For more details, see:

http://rlai.cs.ualberta.ca/RLAI/rlc.html

----------------------------------
Organization Committee
----------------------------------

Adam White, University of Alberta, Alberta, Canada
Richard S. Sutton, University of Alberta, Alberta, Canada
Michael L. Littman, Rutgers University, New Jersey, USA
Doina Precup, Mcgill University , Montreal, Canada
Peter Stone, University of Texas, Austin, Texas, USA

------------------------------------------------
Technical Organization Committee
------------------------------------------------

Andrew Butcher, University of Alberta, Alberta, Canada