The senior organizing committee of the 2009 RL Competition is composed of experienced researchers in the field of reinforcement learning. The organizers also have experience organizing previous workshops (for example, the 2006 NIPS Workshop on Grounding Perception, Knowledge and Cognition in Sensori-Motor Experience, the ALA workshop at AAMAS-09 and the 2008 RL Competition Workshop at ICML 2008). The general chair is David Wingate, a postdoc at MIT.

The technical committee is a seasoned group of capable programmers, composed of previous competitors and compe- tition chairs. Each technical committee member owns one of the six domains, and is charged with development of the domain (parameterizations), integration of the domain with the RL-Glue 3.0 framework, and maintenance / debugging of the domain.

The competition organizers are:

• General chair: David Wingate (MIT)
  David Wingate is a postdoctoral research associate in the Computational Cognitive Science Group at MIT working with Josh Tenenbaum. His research interests lie at the intersection of perception, control and cog- nition, how all three have synergistic effects on learning. Specific interests include reinforcement learning, unsupervised learning of useful knowledge representations (including predictive representations of state and structured nonparametric Bayesian distributions), information theory, manifold learning, kernel meth- ods, massively parallel processing, visual perception, and optimal control. David holds a Ph.D. from the University Michigan and M.S. and B.S. degrees in Computer Science from BYU.
• Technical chair: Carlos Diuk (Rutgers)
  Carlos Diuk is a senior graduate student working with Michael Littman at the Rutgers Laboratory for Real- Life Reinforcement Learning (RL)³, after obtaining his MSc degree from the University of Buenos Aires. His interests include transfer learning (how can an agent "transfer" knowledge obtained while performing a previous task into a new and -somewhat- similar task?) and efficient reinforcement learning (explor- ing how factored state spaces, hierarchies, object-oriented representations and model-based frameworks can be combined to achieve efficient learning). He is an active participant in the reinforcement learning community, having reviewed for numerous conferences and journals.
• Funding: Lihong Li (Rutgers)
  Lihong Li is a PhD candidate at the Rutgers University working with Prof. Michael Littman. Before that, he obtained a MSc degree from the University of Alberta in 2004, and BE from the Tsinghua Uni- versity in 2002. His main interests are in reinforcement learning and machine learning, including: ex- ploration/exploitation tradeoff, value function approximation, feature selection and discovery in reinforce- ment learning, online learning, computational learning theory, and decision-theoretic planning. He is a co-winner of an ICML’08 Best Student Paper Award, and has reviewed (or will review) for several leading conferences (AAAI, ECML, ICML, IJCAI, and NIPS) and journals (DMKD, JAIR, JMLR, and MLJ).
• Website: Jordan Frank (McGill)
  Jordan Frank is a PhD student at McGill University in Montreal, Canada. Jordan works with Profs. Doina Precup and Shie Mannor in the Reasoning and Learning Lab, and his research area is human behavior modeling and reinforcement learning.
• Publicity: Matt Taylor (USC)
  Matthew E. Taylor is a postdoctoral research associate at the University of Southern California, funded by Milind Tambe. He graduated magna cum laude with a double major in computer science and physics from Amherst College in 2001. After working for two years as a software developer, he began his Ph.D. after being awarded the College of Natural Sciences’ MCD fellowship. He received his doctorate from the Department of Computer Sciences at the University of Texas at Austin in the summer of 2008. Current research interests include multi-agent systems, reinforcement learning, and transfer learning.
• Senior technical advisor: Brian Tanner (University of Alberta)
  Brian Tanner is a provisional Ph.D candidate at the University of Alberta. His research focuses on empirical evaluation and comparison of reinforcement learning algorithms. He served as the chair of the technical committee for the 2008 Reinforcement Learning Competition.
• Senior advisor: Doina Precup (McGill)

Each member of the technical committee is responsible for a domain. The members of the technical committee are:

• Brian Tanner - University of Alberta (Polyathlon)
• Adam White - University of Alberta (Polyathlon)
• Marc Lanctot - University of Alberta
• Chris Rayner - University of Alberta (Helicopter)
• Monica Dinculescu - McGill University (Octopus)
• Istvan Szita - Rutgers (Tetris)
• John Asmuth - Rutgers (Mario)
• José Antonio Martín H. - Universidad Complutense de Madrid (Acrobot)