{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,23]],"date-time":"2024-10-23T09:00:10Z","timestamp":1729674010258,"version":"3.28.0"},"reference-count":14,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,12]]},"DOI":"10.1109\/cdc.2011.6161093","type":"proceedings-article","created":{"date-parts":[[2012,3,7]],"date-time":"2012-03-07T21:18:31Z","timestamp":1331155111000},"page":"3862-3869","source":"Crossref","is-referenced-by-count":3,"title":["Stochastic bandits with pathwise constraints"],"prefix":"10.1109","author":[{"given":"Orly","family":"Avner","sequence":"first","affiliation":[]},{"given":"Shie","family":"Mannor","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Mathematical Statistics","year":"1962","author":"wilks","key":"13"},{"key":"14","volume":"28","author":"wozencraft","year":"1965","journal-title":"Principles of Communication Engineering"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/98.788210"},{"key":"12","doi-asserted-by":"publisher","DOI":"10.1287\/opre.37.3.474"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.1023\/A:1013689704352"},{"key":"2","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1007\/978-3-540-75225-7_15","article-title":"Tuning bandit algorithms in stochastic environments","author":"audibert","year":"2007","journal-title":"Algorithmic Learning Theory"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.2307\/1427934"},{"key":"10","first-page":"569","article-title":"Online learning with sample path constraints","volume":"10","author":"mannor","year":"2009","journal-title":"The Journal of Machine Learning Research"},{"key":"7","first-page":"1192","article-title":"A class of steering policies under a recurrence condition","author":"ma","year":"1988","journal-title":"Decision and Control 1988"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1016\/0196-8858(85)90002-8"},{"key":"5","first-page":"1","article-title":"Multi-armed bandit based policies for cognitive radio's decision making issues","author":"jouini","year":"2010","journal-title":"Signals Circuits and Systems (SCS)"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-015-3711-7"},{"key":"9","first-page":"325","article-title":"A geometric approach to multi-criterion reinforcement learning","volume":"5","author":"mannor","year":"2004","journal-title":"The Journal of Machine Learning Research"},{"journal-title":"Implementation Issues for Markov Decision Processes","year":"1986","author":"makowski","key":"8"}],"event":{"name":"2011 50th IEEE Conference on Decision and Control and European Control Conference (CDC-ECC 2011)","start":{"date-parts":[[2011,12,12]]},"location":"Orlando, FL, USA","end":{"date-parts":[[2011,12,15]]}},"container-title":["IEEE Conference on Decision and Control and European Control Conference"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6149620\/6159299\/06161093.pdf?arnumber=6161093","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,20]],"date-time":"2017-06-20T15:20:27Z","timestamp":1497972027000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6161093\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,12]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1109\/cdc.2011.6161093","relation":{},"subject":[],"published":{"date-parts":[[2011,12]]}}}