{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:32:16Z","timestamp":1729675936387,"version":"3.28.0"},"reference-count":26,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,6]]},"DOI":"10.1109\/fuzzy.2011.6007675","type":"proceedings-article","created":{"date-parts":[[2011,9,12]],"date-time":"2011-09-12T20:27:07Z","timestamp":1315859227000},"page":"1422-1429","source":"Crossref","is-referenced-by-count":2,"title":["Fuzzy reinforcement learning control for decentralized partially observable Markov decision processes"],"prefix":"10.1109","author":[{"given":"Rajneesh","family":"Sharma","sequence":"first","affiliation":[]},{"given":"Matthijs T. J.","family":"Spaan","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Game Theory","year":"1982","author":"owen","key":"19"},{"key":"17","article-title":"Bounded policy iteration for decentralized POMDPs","author":"bernstein","year":"2005","journal-title":"Proc Int Joint Conf on Artificial Intelligence"},{"journal-title":"Fuzzy Logic with Engineering Applications","year":"2004","author":"ross","key":"18"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9103-z"},{"key":"16","article-title":"An optimal best-first search algorithm for solving infinite horizon DEC-POMDPs","author":"szer","year":"2005","journal-title":"European Conference on Machine Learning"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/TFUZZ.2007.903323"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-007-9026-5"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/72.159070"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1109\/5326.704563"},{"key":"21","article-title":"Bounded finite state controllers","volume":"16","author":"poupart","year":"2004","journal-title":"Advances in neural information processing systems"},{"key":"20","article-title":"Approximate solutions for partially observable stochastic games with common payoffs","author":"emery-montemerlo","year":"2004","journal-title":"Proc 1st Int Conf Autonomous Agents Multiagent Syst"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2007.368202"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC.2009.4917494"},{"key":"24","article-title":"Rollout sampling policy iteration for decentralized POMDPs","author":"wu","year":"2010","journal-title":"Proc of Uncertainty in Artificial Intelligence"},{"key":"25","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1007\/11559221_31","article-title":"A multiagent fuzzy reinforcement learning method for continuous domains","author":"duman","year":"2005","journal-title":"Multi-Agent Systems and Applications III"},{"key":"26","doi-asserted-by":"publisher","DOI":"10.2316\/Journal.206.2006.2.206-2795"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.4.819.297"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1109\/9780470544785"},{"key":"1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes-Discrete Stochastic Dynamic Programming"},{"key":"7","first-page":"1789","article-title":"Collaborative multiagent reinforcement learning by payoff propagation","volume":"7","author":"kok","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"5"},{"key":"4","article-title":"Planning, learning and coordination in multiagent decision processes","author":"boutilier","year":"1996","journal-title":"Proc Theor Aspects Rationality Knowl"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022676722315"},{"key":"8","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1613\/jair.2447","article-title":"Optimal and approximate Q-value functions for decentralized POMDPs","volume":"32","author":"oliehoek","year":"2008","journal-title":"Journal of Artificial Intelligence Research"}],"event":{"name":"2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","start":{"date-parts":[[2011,6,27]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2011,6,30]]}},"container-title":["2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5976945\/6007305\/06007675.pdf?arnumber=6007675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,4]],"date-time":"2021-12-04T13:50:41Z","timestamp":1638625841000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6007675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/fuzzy.2011.6007675","relation":{},"subject":[],"published":{"date-parts":[[2011,6]]}}}