Sciweavers

Share
ICML
2005
IEEE

Bayesian sparse sampling for on-line reward optimization

13 years 2 months ago
Bayesian sparse sampling for on-line reward optimization
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.
Tao Wang, Daniel J. Lizotte, Michael H. Bowling, D
Added 17 Nov 2009
Updated 17 Nov 2009
Type Conference
Year 2005
Where ICML
Authors Tao Wang, Daniel J. Lizotte, Michael H. Bowling, Dale Schuurmans
Comments (0)
books