Journal Articles
Correcting Evaluation Bias of Relational Classifiers with Network Cross Validation
Jennifer Neville, Brian Gallagher, Tina Eliassi-Rad, and Tao Wang.
Knowledge and Information Systems, 2011.
Dynamic Motion Models in Monte Carlo Localization
Adam Milstein and Tao Wang.
Integrated Computer-Aided Engineering, Vol. 14, No. 3, pages 243-262, 2007.
Speaker Recognition and its Applications
Tao Wang and Naiping Xu.
Journal of Microprocessors, Vol. 4, pages 50-54, November 1997.
Selected Conference Publications
Correcting Bias in Statistical Tests for Network Classifier Evaluation
Tao Wang, Jennifer Neville, Brian Gallagher, and Tina Eliassi-Rad.
In the proceeding of European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD), pages 506-521, 2011.
[pdf] [ECML11 talk] [Poster]
Stable Dual Dynamic Programming
Tao Wang, Daniel Lizotte, Michael Bowling, and Dale Schuurmans.
In Proceedings of Advances in Neural Information Processing Systems 20
(NIPS), pages 1569-1576, 2008 [pdf] [Poster][Spotlight]
Dual Representations for Dynamic Programming and Reinforcement Learning
Tao Wang, Michael Bowling, and Dale Schuurmans.
2007 IEEE International Symposium on Approximate Dynamic Programming and Reinforcement Learning [pdf]
Winner of the Best Student Paper Award
Automatic Gait Optimization with Gaussian Process Regression
Daniel Lizotte, Tao Wang, Michael Bowling, and Dale Schuurmans.
In Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI 2007) [pdf]
Compact, Convex Upper Bound Iteration for Approximate POMDP Planning
Tao Wang, Pascal Poupart, Michael Bowling, and Dale Schuurmans.
In Proceedings of the Twenty-First National Conference on Artificial Intelligence
(AAAI 2006) [pdf] [AAAI06 talk]
Action Selection in Bayesian Reinforcement Learning
Tao Wang.
In Proceedings of the Twenty-First National Conference on Artificial Intelligence
(AAAI 2006) [pdf] [AAAI06-DC talk]
Localization With Dynamic Motion Models: Determining motion model parameters dynamically in Monte Carlo Localization
Adam Milstein and Tao Wang.
In Proc. of the Third International Conference on Informatics in Control, Automation and Robotics (ICINCO 2006) [pdf]
Bayesian Sparse Sampling for On-line Reward Optimization,
Tao Wang, Daniel Lizotte, Michael Bowling, and Dale Schuurmans.
In Proceedings of the Twenty-second International Conference on Machine Learning (ICML 2005)
[pdf] [ICML05 talk] [NIPS05-workshop talk]
Collective Sorting with Multiple Robots,
Tao Wang and Hong Zhang.
In Proceedings of the First IEEE International Conference on Robotics and Biomimetics (ROBIO 2004) [pdf]
Multi-Robot Collective Sorting with Local Sensing,
Tao Wang and Hong Zhang.
In Proceedings of IEEE Intelligent Automation Conference (IAC 2003) [pdf]
Experimental Results Towards Content-Based Sub-Image Retrieval,
Tao Wang, Juhua Shi, and Mario A. Nascimento.
In Proceedings of the International Conference on Information Technology: Coding and Computing (ITCC 2002) [pdf]
PhD Dissertation
New Representations and Approximations for Sequential Decision Making under Uncertainty
Department of Compuitng Science, University of Alberta, 2007 [pdf]
Finalist for the Department of Computing Science 2007 Ph.D. Thesis Award
My dissertation research addresses the challenge of scaling up algorithms for sequential decision making under uncertainty. In my thesis, I developed new approximation strategies for planning and learning in the presence of uncertainty while maintaining useful theoretical properties that allow larger problems to be tackled than is practical with exact methods. In particular, my research tackles three outstanding issues in sequential decision making in uncertain environments: performing stable generalization during off-policy updates, balancing exploration with exploitation, and handling partial observability of the environment.
The first key contribution of my thesis is the development of novel dual representations and algorithms for planning and learning in stochastic environments. Another key contribution of my thesis is the development of a practical action selection strategy that addresses the well known exploration versus exploitation tradeoff in reinforcement learning. Finally my thesis also develops a new approach to approximate planning in partially observable Markov decision processes.
Book Chapters
Biologically Inspired Collective Robotics.
C. Ronald Kube, Chris A. C. Parker, Tao Wang, and Hong Zhang.
Chapter 15 in Recent Developments in Biologically Inspired Computing,
Leandro Nunes de Castro and Fernando J. Von Zuben, eds.
Publisher: Idea Group Inc. (IGI). (2004). ISBN: 159140313-8