View Document Preview and Link Document Date: 2009-03-01 20:57:56 Open Document File Size: 656,54 KB Share Result on Facebook
Company Simmons / / / Facility Engineering Mississippi State University / Computer Science University of Massachusetts Amherst / University of Massachusetts Amherst / / IndustryTerm higher quality solutions / nontrivial optimal algorithm / approximate algorithms / agent algorithms / incremental pruning algorithm / policy iteration algorithm / forward search / policy search / concise and higher-valued solutions / correlation device / space exploration systems / dynamic programming algorithm / e - commerce / dynamic programming algorithms / policy iteration algorithms / relaxed region algorithms / bounded policy iteration algorithm / value iteration algorithm / multi-robot systems / pruning algorithm / / MusicAlbum DP / / Organization Computer Science University of Massachusetts Amherst / AI Access Foundation / Department of CS / Department of Computer Science / Mississippi State University / University of Massachusetts Amherst / / Person Christopher Amato / max b / Daniel S. Bernstein / Ai / / Position local controller / finite-state controller / controller / / ProvinceOrState Mississippi / Massachusetts / / PublishedMedium Journal of Artificial Intelligence Research / / Technology policy iteration algorithms / POMDP algorithm / pruning algorithm / relaxed region algorithms / Witness algorithm / dynamic programming algorithms / artificial intelligence / bounded policy iteration algorithm / incremental pruning algorithm / value iteration algorithm / dynamic programming algorithm / policy iteration algorithm / DEC-POMDPs agent algorithms / / SocialTag 
Journal of Artificial Intelligence Research Submitted 8/08; published 2/09 Policy Iteration for Decentralized Control of Markov Decision Processes