{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T09:12:47Z","timestamp":1730193167761,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2007,7]]},"DOI":"10.1109\/acc.2007.4282586","type":"proceedings-article","created":{"date-parts":[[2007,8,8]],"date-time":"2007-08-08T16:01:54Z","timestamp":1186588914000},"page":"2428-2433","source":"Crossref","is-referenced-by-count":0,"title":["Solving MDPs using Two-timescale Simulated Annealing with Multiplicative Weights"],"prefix":"10.1109","author":[{"given":"Mohammed Shahid","family":"Abdulla","sequence":"first","affiliation":[]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1137\/S036301299731669X"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2004.825622"},{"key":"ref10","article-title":"An Asymptotically Efficient Algorithm for Finite Horizon Stochastic Dynamic Programming Problems","author":"chang","year":"2003","journal-title":"Proc of the 42nd IEEE CDC 2003"},{"key":"ref6","article-title":"Reinforcement learning based algorithms for average cost markov decision processes","author":"abdulla","year":"2006","journal-title":"Accepted for publication in Discrete Event Dynamical Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.2004.1429441"},{"key":"ref5","article-title":"An Actor-Critic Algorithm for Finite Horizon Markov Decision Processes","author":"bhatnagar","year":"2006","journal-title":"Proceedings of the 45th IEEE-CDC"},{"article-title":"Introduction to Probability Models, 7\/e","year":"2000","author":"ross","key":"ref12"},{"journal-title":"Learning Dynamic Prices In Electronic Markets","year":"2004","author":"raju ch","key":"ref8"},{"key":"ref7","article-title":"An Actor-Critic Algorithm for Finite Horizon Markov Decision Processes","author":"bhatnagar","year":"2006","journal-title":"submitted"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"ref9","volume":"i","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"ref1"}],"event":{"name":"2007 American Control Conference","start":{"date-parts":[[2007,7,9]]},"location":"New York, NY, USA","end":{"date-parts":[[2007,7,13]]}},"container-title":["2007 American Control Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4282134\/4282135\/04282586.pdf?arnumber=4282586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,3,15]],"date-time":"2017-03-15T20:41:07Z","timestamp":1489610467000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/4282586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2007,7]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/acc.2007.4282586","relation":{},"ISSN":["0743-1619"],"issn-type":[{"type":"print","value":"0743-1619"}],"subject":[],"published":{"date-parts":[[2007,7]]}}}