{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T19:11:09Z","timestamp":1729624269126,"version":"3.28.0"},"reference-count":20,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2008,12]]},"DOI":"10.1109\/wsc.2008.4736109","type":"proceedings-article","created":{"date-parts":[[2009,1,14]],"date-time":"2009-01-14T18:48:38Z","timestamp":1231958918000},"page":"525-531","source":"Crossref","is-referenced-by-count":11,"title":["On step sizes, stochastic shortest paths, and survival probabilities in Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Abhijit","family":"Gosavi","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"19"},{"journal-title":"Introduction to Probability Models","year":"1997","author":"ross","key":"17"},{"key":"18","first-page":"473","article-title":"average-reward reinforcement learning for variance-penalized markov decision problems","author":"sato","year":"2001","journal-title":"Proceedings of the 18th International Conference on Machine Learning"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.2307\/2975974"},{"key":"16","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1007\/b100669"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50021-0"},{"year":"0","key":"11"},{"year":"0","key":"12"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012995282784"},{"journal-title":"Learning from delayed rewards","year":"1989","author":"watkins","key":"20"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1287\/moor.27.2.294.324"},{"journal-title":"Dynamic Programming and Optimal Control","year":"1995","author":"bertsekas","key":"1"},{"key":"10","doi-asserted-by":"crossref","first-page":"1321","DOI":"10.1016\/j.automatica.2006.02.006","article-title":"a risk-sensitive approach to total productive maintenance","volume":"42","author":"gosavi","year":"2006","journal-title":"Automatica"},{"key":"7","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1613\/jair.1666","article-title":"risk-sensitive reinforcement learning applied to control under constraints","volume":"24","author":"geibel","year":"2005","journal-title":"Journal of Artificial Intelligence Research"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1287\/moor.14.1.147"},{"key":"5","first-page":"1","article-title":"learning rates for q- learning","volume":"5","author":"even-dar","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012997331639"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1016\/S0377-2217(02)00874-3"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1023\/B:MACH.0000019802.64038.6c"}],"event":{"name":"2008 Winter Simulation Conference (WSC)","start":{"date-parts":[[2008,12,7]]},"location":"Miami, FL, USA","end":{"date-parts":[[2008,12,10]]}},"container-title":["2008 Winter Simulation Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/4712635\/4736042\/04736109.pdf?arnumber=4736109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,17]],"date-time":"2019-05-17T06:46:23Z","timestamp":1558075583000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/4736109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2008,12]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/wsc.2008.4736109","relation":{},"subject":[],"published":{"date-parts":[[2008,12]]}}}