Action Selection in Bayesian Reinforcement Learning


My research attempts to address on-line action selection in reinforcement learning from a Bayesian perspective. The idea is to develop more effective action selection techniques by exploiting information in a Bayesian posterior, while also selecting actions by growing an adaptive, sparse lookahead tree. I further augment the approach by considering a new… (More)
View Slides


Cite this paper

@inproceedings{Wang2006ActionSI, title={Action Selection in Bayesian Reinforcement Learning}, author={Tao Wang}, booktitle={AAAI}, year={2006} }