{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T00:13:48Z","timestamp":1729642428856,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2016,3]]},"DOI":"10.1109\/icit.2016.7474986","type":"proceedings-article","created":{"date-parts":[[2016,6,23]],"date-time":"2016-06-23T16:36:46Z","timestamp":1466699806000},"page":"1522-1526","source":"Crossref","is-referenced-by-count":0,"title":["A special case of partially observable Markov decision processes problem by event-based optimization"],"prefix":"10.1109","author":[{"given":"Junyu","family":"Zhang","sequence":"first","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50052-9"},{"journal-title":"Introduction to Stochastic Dynamic Programming","year":"1983","author":"ross","key":"ref11"},{"journal-title":"The optimal control of partially observable Markov Decision Processes","year":"1971","author":"sondik","key":"ref12"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2008.919557"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1109\/TAC.2007.915168","article-title":"The nth-Order Bias Optimality for Multi-Chain Markov Decision Processes","volume":"53","author":"cao","year":"2008","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907500"},{"key":"ref5","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1109\/TAC.2013.2293397","article-title":"Partial-Information State-Based Optimization of Partially Observable Markov Decision Processes and the Separation Principle","volume":"59","author":"cao","year":"2014","journal-title":"IEEE Transactions on Automatic Control"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/S0004-3702(98)00023-X"},{"key":"ref7","first-page":"345","article-title":"Reinforcement Learning Algorithm for Partially Observable Markov Decision Problems","volume":"7","author":"jaakkola","year":"1995","journal-title":"Advances in neural information processing systems"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s10626-004-6211-4"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008260528575"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-27170-8_21"}],"event":{"name":"2016 IEEE International Conference on Industrial Technology (ICIT)","start":{"date-parts":[[2016,3,14]]},"location":"Taipei, Taiwan","end":{"date-parts":[[2016,3,17]]}},"container-title":["2016 IEEE International Conference on Industrial Technology (ICIT)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7468873\/7474713\/07474986.pdf?arnumber=7474986","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,24]],"date-time":"2017-06-24T16:56:38Z","timestamp":1498323398000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7474986\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,3]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/icit.2016.7474986","relation":{},"subject":[],"published":{"date-parts":[[2016,3]]}}}