{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T02:00:51Z","timestamp":1729648851395,"version":"3.28.0"},"reference-count":24,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,10]]},"DOI":"10.1109\/allerton.2012.6483246","type":"proceedings-article","created":{"date-parts":[[2013,3,27]],"date-time":"2013-03-27T20:58:45Z","timestamp":1364417925000},"page":"400-405","source":"Crossref","is-referenced-by-count":7,"title":["A novel Q-learning algorithm with function approximation for constrained Markov decision processes"],"prefix":"10.1109","author":[{"given":"K.","family":"Lakshmanan","sequence":"first","affiliation":[]},{"given":"Shalabh","family":"Bhatnagar","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"19"},{"key":"22","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-1098(99)00099-0"},{"key":"17","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes Discrete Stochastic Dynamic Programming"},{"journal-title":"An Introduction to Queueing Networks","year":"1988","author":"walrand","key":"23"},{"key":"18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"24","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"journal-title":"Microeconomic Theory","year":"1995","author":"mas-colell","key":"15"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72927-3_23"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2004.08.007"},{"key":"11","article-title":"Approximate dynamic programming","volume":"2","author":"bertsekas","year":"2011","journal-title":"Dynamic Programming and Optimal Control"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"12"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-377-6.50013-X"},{"key":"20","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0005-1098(96)00149-5","article-title":"A one-measurement form of simultaneous perturbation stochastic approximation","volume":"33","author":"spall","year":"1997","journal-title":"Automatica"},{"journal-title":"Constrained Markov Decision Processes","year":"1999","author":"altman","key":"2"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012999361974"},{"key":"10","volume":"2","author":"bertsekas","year":"2007","journal-title":"Dynamic Programming and Optimal Control"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-012-9989-5"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1145\/858481.858486"},{"key":"9","volume":"1","author":"bertsekas","year":"2005","journal-title":"Dynamic Programming and Optimal Control"},{"key":"8","article-title":"An online convergent Qlearning algorithm with linear function approximation","author":"bhatnagar","year":"2012","journal-title":"Technical Report No IISc-CSA-SSL-TR-2012-3 Stochastic Systems Laboratory"}],"event":{"name":"2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)","start":{"date-parts":[[2012,10,1]]},"location":"Monticello, IL, USA","end":{"date-parts":[[2012,10,5]]}},"container-title":["2012 50th Annual Allerton Conference on Communication, Control, and Computing (Allerton)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6475439\/6483185\/06483246.pdf?arnumber=6483246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,12]],"date-time":"2022-02-12T14:43:53Z","timestamp":1644677033000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6483246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,10]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/allerton.2012.6483246","relation":{},"subject":[],"published":{"date-parts":[[2012,10]]}}}