My PhD Thesis:

Exponential Family Predictive Representations of State

I am the general chair of the 2009 Reinforcement Learning Competition, which started on Feb. 4 and ends on June 8. Check it out and compete for fame, fortune, and reasonably cool prizes!

I co-organized the NIPS 2006 Workshop on Grounding Perception, Knowledge and Cognition in Sensori-Motor Experience, along with Brian Tanner and Michael James. Please check the website for slides, posters and papers.

Prioritization Methods for Accelerating MDP Solvers
David Wingate and Kevin D. Seppi
Journal of Machine Learning Research 6(May):851-881, 2005.

The Infinite Latent Events Model
David Wingate, Noah D. Goodman, Daniel M. Roy and Joshua B. Tenenbaum
Uncertainty in Artificial Intelligence (UAI), 2009.

A Bayesian Sampling Approach to Exploration in Reinforcement Learning
John Asmuth, Lihong Li, Michael L. Littman, Ali Nouri and David Wingate,
Uncertainty in Artificial Intelligence (UAI), 2009.

Efficiently Learning Linear-Linear Exponential Family Predictive Representations of State
David Wingate and Satinder Singh
International Conference on Machine Learning (ICML), 2008.

Sigma Point Policy Iteration
Michael Bowling, Alborz Geramifard and David Wingate
Autonomous Agents and Multiagent Systems (AAMAS), 2008.

Exponential Family Predictive Representations of State
David Wingate and Satinder Singh
Neural Information Processing Systems (NIPS), 2007.

On Discovery and Learning of Models with Predictive Representations of State for Agents with Continuous Actions and Observations
David Wingate and Satinder Singh
International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1128-1135, 2007.

Relational Knowledge with Predictive State Representations
David Wingate, Vishal Soni, Britton Wolfe and Satinder Singh
International Joint Conference on Artificial Intelligence (IJCAI), pages 2035-2040, 2007.

Mixtures of Predictive Linear Gaussian Models for Nonlinear Stochastic Dynamical Systems
David Wingate and Satinder Singh
National Conference on Artificial Intelligence (AAAI), 2006.

Kernel Predictive Linear Gaussian Models for Nonlinear Stochastic Dynamical Systems
David Wingate and Satinder Singh
International Conference on Machine Learning (ICML), pages 1017 - 1024, 2006.

Predictive Linear-Gaussian Models of Stochastic Dynamical Systems
Matt Rudary, Satinder Singh and David Wingate
Uncertainty in Artificial Intelligence (UAI), pages 501-508, 2005.

Prioritized Multiplicative Schwarz Procedures for Solutions to General Linear Systems
David Wingate, Nathaniel Powell, Quinn Snell and Kevin D. Seppi
International Parallel and Distributed Processing Symposium (IPDPS), 2005.

P3VI: A Partitioned, Prioritized, Parallel Value Iterator
David Wingate and Kevin D. Seppi
International Conference on Machine Learning (ICML), pages 863-870, 2004.

Variable Resolution Discretization in the Joint Space
Christopher K. Monson, David Wingate, Kevin D. Seppi, and Todd S. Peterson
International Conference on Machine Learning and Applications, 2004.

Efficient Value Iteration Using Partitioned Models
David Wingate and Kevin D. Seppi
International Conference on Machine Learning and Applications, pages 53-59, 2003.
Best paper award.

Cache Performance of Priority Metrics for MDP Solvers
David Wingate and Kevin D. Seppi
AAAI Workshop on Learning and Planning in Markov Processes, pages 103-106, 2004.

Solving Large MDPs Quickly with Partitioned Value Iteration

Some neat videos and source code are available.