{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T22:36:30Z","timestamp":1729636590986,"version":"3.28.0"},"reference-count":13,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2011,4]]},"DOI":"10.1109\/adprl.2011.5967377","type":"proceedings-article","created":{"date-parts":[[2011,8,3]],"date-time":"2011-08-03T21:40:00Z","timestamp":1312407600000},"page":"56-61","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive sample collection using active learning for kernel-based approximate policy iteration"],"prefix":"10.1109","author":[{"given":"Chunming","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"family":"Haiyun Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"733","article-title":"Online exploration in least-squares policy iteration","volume":"2","author":"li","year":"0","journal-title":"Proceedings of the 3rd International Conference on Autonomous Agents and Multi-Agent Systems"},{"article-title":"Statistical Learning Theory","year":"1998","author":"vapnik","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2004.830985"},{"key":"ref13","first-page":"486","article-title":"Online leastsquares policy iteration for reinforcement learning control","author":"busoniu","year":"0","journal-title":"Proceedings 2010 American Control Conference (ACC-10)"},{"key":"ref4","article-title":"Reinforcement Learning","author":"sutton","year":"1998","journal-title":"Introduction"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1613\/jair.301","article-title":"Reinforcement learning: A survey","volume":"4","author":"kaelbling","year":"1996","journal-title":"Journal of Artificial Intelligence Research"},{"key":"ref6","first-page":"213","article-title":"R-MA X-A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"0","journal-title":"Journal of Machine Learning Research"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017984413808"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390194"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102459"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2007.899161"},{"key":"ref1","first-page":"1107","article-title":"Least-squares policy iteration","volume":"4","author":"lagoudakis","year":"2003","journal-title":"Journal of Machine Learning Research"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.12.010"}],"event":{"name":"2011 Ieee Symposium On Adaptive Dynamic Programming And Reinforcement Learning","start":{"date-parts":[[2011,4,11]]},"location":"Paris, France","end":{"date-parts":[[2011,4,15]]}},"container-title":["2011 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/5958170\/5967347\/05967377.pdf?arnumber=5967377","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,13]],"date-time":"2019-06-13T14:53:25Z","timestamp":1560437605000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/5967377\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2011,4]]},"references-count":13,"URL":"https:\/\/doi.org\/10.1109\/adprl.2011.5967377","relation":{},"subject":[],"published":{"date-parts":[[2011,4]]}}}