Bayesian Sparse Sampling for On-Line Reward Optimization
- Tao Wang, University of Alberta
- Dan Lizotte, University of Michigan
- Michael Bowling, University of Alberta
- Dale Schuurmans, AICML
We present an efficient “sparse sampling” technique for approximating Bayes optimal decision making in reinforcement learning, addressing the well known exploration versus exploitation tradeoff. Our approach combines sparse sampling with Bayesian exploration to achieve improved decision making while controlling computational cost. The idea is to grow a sparse lookahead tree, intelligently, by exploiting information in a Bayesian posterior—rather than enumerate action branches (standard sparse sampling) or compensate myopically (value of perfect information). The outcome is a flexible, practical technique for improving action selection in simple reinforcement learning scenarios.
Citation
T. Wang, D. Lizotte, M. Bowling, D. Schuurmans. "Bayesian Sparse Sampling for On-Line Reward Optimization". International Conference on Machine Learning (ICML), Bonn, Germany, pp 961-968, January 2005.Keywords: | machine learning |
Category: | In Conference |
BibTeX
@incollection{Wang+al:ICML05, author = {Tao Wang and Dan Lizotte and Michael Bowling and Dale Schuurmans}, title = {Bayesian Sparse Sampling for On-Line Reward Optimization}, Pages = {961-968}, booktitle = {International Conference on Machine Learning (ICML)}, year = 2005, }Last Updated: April 24, 2007
Submitted by AICML Admin Assistant