{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T15:45:29Z","timestamp":1729611929054,"version":"3.28.0"},"reference-count":27,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1109\/wsc.2011.6147989","type":"proceedings-article","created":{"date-parts":[[2012,2,9]],"date-time":"2012-02-09T17:20:26Z","timestamp":1328808026000},"page":"2860-2871","source":"Crossref","is-referenced-by-count":1,"title":["Stochastic policy search for variance-penalized semi-Markov control"],"prefix":"10.1109","author":[{"given":"Abhijit","family":"Gosavi","sequence":"first","affiliation":[]},{"given":"Mandar","family":"Purohit","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","article-title":"Adaptive Critics for Airline Revenue Management","author":"gosavi","year":"2007","journal-title":"Proceedings of 18th Annual Conference of the Production and Operations Management Society"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2008.4736109"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/WSC.2009.5429344"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1080\/07408170490438672"},{"key":"ref14","article-title":"Value Iteration on Two Time-Scales for Variance-Penalized Markov Control","author":"gosavi","year":"2010","journal-title":"Proc Proceedings of the 2010 Industrial Engineering Research Conference"},{"journal-title":"Introduction to Probability","year":"1997","author":"grinstead","key":"ref15"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2003.815008"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"key":"ref18","first-page":"77","article-title":"Portfolio Selection","volume":"7","author":"markowitz","year":"1952","journal-title":"Journal of Finance"},{"journal-title":"Learning Automata An Introduction","year":"1989","author":"narendra","key":"ref19"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(75)90029-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1986.1104342"},{"key":"ref3","first-page":"1995","author":"bertsekas","year":"0","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.14.1.147"},{"key":"ref5","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-84628-690-2","author":"chang","year":"2007","journal-title":"Simulation-Based Algorithms for Markov Decision Processes"},{"key":"ref8","first-page":"162","article-title":"Reinforcement Learning via bounded risk","author":"geibel","year":"2001","journal-title":"ICML01"},{"key":"ref7","first-page":"197","article-title":"Multi-criteria reinforcement learning","author":"gabor","year":"1998","journal-title":"Proc of 15th International Conf on Machine Learning"},{"journal-title":"Neuro-Dynamic Programming Belmont","year":"1996","author":"bertsekas","key":"ref2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2006.02.006"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"Journal of Artificial Intelligence"},{"key":"ref20","first-page":"1031","article-title":"Risk-sensitive Reinforcement Learning","volume":"2","author":"neueier","year":"1999","journal-title":"Advances in NIPS"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2006.02.023"},{"article-title":"Stochastic approximation methods for risk-sensitive control of discrete-event systems","year":"2006","author":"purohit","key":"ref21"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/0471722138"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/9.119632"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/047001363X"},{"journal-title":"Reinforcement Learning[M]","year":"1998","author":"sutton","key":"ref25"}],"event":{"name":"2011 Winter Simulation Conference - (WSC 2011)","start":{"date-parts":[[2011,12,11]]},"location":"Phoenix, AZ, USA","end":{"date-parts":[[2011,12,14]]}},"container-title":["Proceedings of the 2011 Winter Simulation Conference (WSC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6135535\/6147014\/06147989.pdf?arnumber=6147989","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,23]],"date-time":"2019-06-23T08:04:42Z","timestamp":1561277082000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6147989\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/wsc.2011.6147989","relation":{},"subject":[],"published":{"date-parts":[[2011,12]]}}}