{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T16:07:23Z","timestamp":1729613243194,"version":"3.28.0"},"reference-count":21,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2009,5]]},"DOI":"10.1109\/gamenets.2009.5137416","type":"proceedings-article","created":{"date-parts":[[2009,7,1]],"date-time":"2009-07-01T15:05:14Z","timestamp":1246460714000},"page":"314-322","source":"Crossref","is-referenced-by-count":10,"title":["Online learning in Markov decision processes with arbitrarily changing rewards and transitions"],"prefix":"10.1109","author":[{"given":"Jia Yuan","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shie","family":"Mannor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"19","doi-asserted-by":"publisher","DOI":"10.2307\/3212261"},{"key":"17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcss.2004.10.016"},{"key":"18","volume":"2","author":"bertsekas","year":"2001","journal-title":"Dynamic Programming and Optimal Control"},{"key":"15","first-page":"1537","article-title":"the robustness-performance tradeoff in markov decision processes","author":"xu","year":"2006","journal-title":"NIPS"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4054-9"},{"key":"13","doi-asserted-by":"publisher","DOI":"10.1109\/18.720535"},{"key":"14","doi-asserted-by":"publisher","DOI":"10.1006\/inco.1994.1009"},{"key":"11","first-page":"97","article-title":"approximation to bayes risk in repeated play","volume":"3","author":"hannan","year":"1957","journal-title":"Contributions to the Theory of Games"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1007\/0-8176-4429-6_19"},{"key":"21","article-title":"locally weighted learning","author":"atkeson","year":"1997","journal-title":"Artificial Intelligence Review"},{"key":"3","first-page":"401","article-title":"experts in a markov decision process","author":"even-dar","year":"2004","journal-title":"NIPS"},{"article-title":"on-line markov decision processes","year":"0","author":"even-dar","key":"20"},{"key":"2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1095"},{"key":"1","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","author":"puterman","year":"1994","journal-title":"Markov Decision Processes"},{"journal-title":"Neuro-Dynamic Programming","year":"1996","author":"bertsekas","key":"10"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539701398375"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1287\/opre.1050.0216"},{"key":"5","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546921"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1287\/moor.28.2.327.14483"},{"year":"0","key":"9"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1162\/153244303765208377"}],"event":{"name":"2009 International Conference on Game Theory for Networks (GameNets)","start":{"date-parts":[[2009,5,13]]},"location":"Istanbul, Turkey","end":{"date-parts":[[2009,5,15]]}},"container-title":["2009 International Conference on Game Theory for Networks"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5076471\/5137364\/05137416.pdf?arnumber=5137416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,18]],"date-time":"2017-06-18T21:28:41Z","timestamp":1497821321000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5137416\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2009,5]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/gamenets.2009.5137416","relation":{},"subject":[],"published":{"date-parts":[[2009,5]]}}}