{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T20:09:21Z","timestamp":1773864561467,"version":"3.50.1"},"reference-count":25,"publisher":"Elsevier BV","issue":"5","license":[{"start":{"date-parts":[[2001,12,1]],"date-time":"2001-12-01T00:00:00Z","timestamp":1007164800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems & Control Letters"],"published-print":{"date-parts":[[2001,12]]},"DOI":"10.1016\/s0167-6911(01)00152-9","type":"journal-article","created":{"date-parts":[[2002,7,25]],"date-time":"2002-07-25T12:45:34Z","timestamp":1027601134000},"page":"339-346","source":"Crossref","is-referenced-by-count":27,"title":["A sensitivity formula for risk-sensitive cost and the actor\u2013critic algorithm"],"prefix":"10.1016","volume":"44","author":[{"given":"V.S.","family":"Borkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/S0167-6911(01)00152-9_BIB1","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1016\/S0304-4149(00)00032-6","article-title":"Multiplicative ergodicity and large deviations for an irreducible Markov chain","volume":"90","author":"Balaji","year":"2000","journal-title":"Stochastic Process. Appl."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB2","first-page":"835","article-title":"Neuron-like elements that can solve difficult learning control problems","volume":"13","author":"Barto","year":"1983","journal-title":"IEEE Trans. Systems Man Cybernet."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB3","series-title":"Adaptive Algorithms and Stochastic Approximation","author":"Benveniste","year":"1990"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB4","series-title":"Neurodynamic Programming","author":"Bertsekas","year":"1996"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB5","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1007\/s001860050094","article-title":"Risk sensitive control of finite state Markov chains in discrete time, with applications to portfolio management","volume":"50","author":"Bielecki","year":"1999","journal-title":"Math. Methods Oper. Res."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB6","doi-asserted-by":"crossref","first-page":"291","DOI":"10.1016\/S0167-6911(97)90015-3","article-title":"Stochastic approximation with two time scales","volume":"29","author":"Borkar","year":"1997","journal-title":"Systems Control Lett."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB7","unstructured":"V.S. Borkar, Asynchronous stochastic approximation, SIAM J. Control Optim. 36 (1998) 840\u2013851 (Erratum: 38 (2000) 662\u2013663)."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB8","unstructured":"V.S. Borkar, Q-learning for risk sensitive control, Math. Oper. Res., submitted for publication."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB9","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1137\/S0363012997331639","article-title":"The O.D.E. method for convergence of stochastic approximation and reinforcement learning","volume":"38","author":"Borkar","year":"2000","journal-title":"SIAM J. Control Optim."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB10","unstructured":"V.S. Borkar, S.P. Meyn, Risk sensitive optimal control for Markov decision processes with monotone cost, Math. Oper. Res., submitted for publication."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB11","doi-asserted-by":"crossref","first-page":"1382","DOI":"10.1109\/9.633827","article-title":"Perturbation realization, potentials and sensitivity analysis of Markov processes","volume":"42","author":"Cao","year":"1997","journal-title":"IEEE Trans. Automat. Control"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB12","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/BF01211853","article-title":"Connections between stochastic control and dynamic games","volume":"9","author":"Dai Pra","year":"1996","journal-title":"Math. Control Signals Systems"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB13","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1137\/S0363012997320614","article-title":"Risk-sensitive control of discrete time Markov processes with infinite horizon","volume":"38","author":"Di Masi","year":"1999","journal-title":"SIAM J. Control Optim."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB14","doi-asserted-by":"crossref","first-page":"1790","DOI":"10.1137\/S0363012995291622","article-title":"Risk-sensitive control of finite state machines on an infinite horizon I","volume":"35","author":"Fleming","year":"1997","journal-title":"SIAM J. Control Optim."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB15","doi-asserted-by":"crossref","unstructured":"P.W. Glynn, Stochastic approximation for Monte Carlo optimization, Proceedings of the 1986 Winter Simulation Conference, 1986, pp. 285\u2013289.","DOI":"10.1145\/318242.318459"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB16","unstructured":"D. Hernandez-Hernandez, S.I. Marcus, Risk sensitive control of Markov processes in countable state space, Systems Control Lett. 29 (1998) 147\u2013155 (Corrigendum: 34 (1998) 105\u2013106)."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB17","unstructured":"T. Jaakola, S.P. Singh, M. Jordan, Reinforcement learning algorithms for partially observable Markov decision problems, in: G. Tesauro, D. Touretzky, T. Leen (Eds.), Advances in Neural Processing Systems, Vol. 7, Morgan Kaufmann, San Francisco, 1995, pp. 345\u2013352."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB18","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1137\/S036301299731669X","article-title":"Actor\u2013critic type learning algorithms for Markov decision processes","volume":"38","author":"Konda","year":"1999","journal-title":"SIAM J. Control Optim."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB19","unstructured":"V.R. Konda, J. Tsitsiklis, Actor\u2013critic algorithms, SIAM J. Control Optim. submitted for publication."},{"key":"10.1016\/S0167-6911(01)00152-9_BIB20","series-title":"Stochastic Approximation Algorithms and Applications","author":"Kushner","year":"1997"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB21","doi-asserted-by":"crossref","first-page":"551","DOI":"10.1109\/TAC.1977.1101561","article-title":"Analysis of recursive stochastic algorithms","volume":"22","author":"Ljung","year":"1977","journal-title":"IEEE Trans. Automat. Control"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB22","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1109\/9.905687","article-title":"Simulation-based optimization of Markov reward processes","volume":"46","author":"Marbach","year":"1998","journal-title":"IEEE Trans. Automat. Control"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB23","series-title":"Markov Decision Processes","author":"Puterman","year":"1994"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB24","series-title":"Reinforcement Learning","author":"Sutton","year":"1998"},{"key":"10.1016\/S0167-6911(01)00152-9_BIB25","series-title":"Risk-Sensitive Optimal Control","author":"Whittle","year":"1990"}],"container-title":["Systems & Control Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167691101001529?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167691101001529?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2019,4,30]],"date-time":"2019-04-30T07:54:16Z","timestamp":1556610856000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167691101001529"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2001,12]]},"references-count":25,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2001,12]]}},"alternative-id":["S0167691101001529"],"URL":"https:\/\/doi.org\/10.1016\/s0167-6911(01)00152-9","relation":{},"ISSN":["0167-6911"],"issn-type":[{"value":"0167-6911","type":"print"}],"subject":[],"published":{"date-parts":[[2001,12]]}}}