{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T06:50:01Z","timestamp":1760079001196,"version":"3.28.0"},"reference-count":10,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1109\/cdc.2003.1273053","type":"proceedings-article","created":{"date-parts":[[2004,7,8]],"date-time":"2004-07-08T20:05:44Z","timestamp":1089317144000},"page":"2823-2828","source":"Crossref","is-referenced-by-count":14,"title":["Policy gradient stochastic approximation algorithms for adaptive control of constrained time varying markov decision processes"],"prefix":"10.1109","volume":"3","author":[{"given":"F.J.","family":"Vazquez Abad","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"V.","family":"Krishnamurthy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","article-title":"Implementation of gradient estimation to a constrained Markov decision problem","author":"vazquez abad","year":"2003","journal-title":"IEEE Conference on Decision and Control"},{"key":"2","doi-asserted-by":"crossref","DOI":"10.1109\/CDC.2002.1184811","article-title":"Self learning control of constrained Markov decision processes - A gradient approach","author":"vazquez abad","year":"2002","journal-title":"IEEE Conference on Decision and Control"},{"journal-title":"Linear and Nonlinear Programming","year":"1984","author":"luenberger","key":"10"},{"key":"1","article-title":"Self learning control of constrained Markov decision processes- a measure valued gradient approach","author":"vazquez abad","year":"2003","journal-title":"IEEE Trans Automatic Control"},{"key":"7","first-page":"71","article-title":"The relations amongst potentials, perturbation analysis and Markov decision processes","volume":"8","author":"cao","year":"1998","journal-title":"J DEDS"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"6"},{"journal-title":"Nonlinear Programming","year":"2000","author":"bertsekas","key":"5"},{"key":"4","article-title":"Direct gradient-based reinforcement learning: I. Gradient estimation algorithms","author":"baxter","year":"1999","journal-title":"Technical Report"},{"key":"9","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4684-9352-8","author":"kushner","year":"1978","journal-title":"Stochastic Approximation Methods for Constrained and Unconstrained Systems"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/78.489036"}],"event":{"name":"42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)","acronym":"CDC-03","location":"Maui, Hawaii, USA"},"container-title":["42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/8969\/28482\/01273053.pdf?arnumber=1273053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,16]],"date-time":"2017-06-16T08:40:25Z","timestamp":1497602425000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/1273053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/cdc.2003.1273053","relation":{},"subject":[]}}