{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,22]],"date-time":"2024-10-22T17:24:20Z","timestamp":1729617860301,"version":"3.28.0"},"reference-count":12,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012,12]]},"DOI":"10.1109\/cdc.2012.6426427","type":"proceedings-article","created":{"date-parts":[[2013,2,8]],"date-time":"2013-02-08T17:05:08Z","timestamp":1360343108000},"page":"5272-5277","source":"Crossref","is-referenced-by-count":21,"title":["Model learning actor-critic algorithms: Performance evaluation in a motion control task"],"prefix":"10.1109","author":[{"given":"Ivo","family":"Grondman","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lucian","family":"Busoniu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robert","family":"Babuska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"3","article-title":"Reinforcement learning architectures","author":"sutton","year":"1992","journal-title":"Proceedings of the International Symposium on Neural Information Processing"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"2"},{"key":"10","doi-asserted-by":"publisher","DOI":"10.1137\/S0363012901385691"},{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033606"},{"key":"6","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2011.5967381"},{"key":"5","first-page":"101","article-title":"Model-based reinforcement learning with an approximate, learned model","author":"kuvayev","year":"1996","journal-title":"Proceedings of the 9th Yale Workshop on Adaptive and Learning Systems"},{"key":"4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"9","doi-asserted-by":"crossref","first-page":"834","DOI":"10.1109\/TSMC.1983.6313077","article-title":"Neuronlike adaptive elements that can solve difficult learning control problems","volume":"13","author":"barto","year":"1983","journal-title":"IEEE Transactions on Systems Man and Cybernetics"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(77)90354-0"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.008"},{"key":"12","doi-asserted-by":"crossref","DOI":"10.1201\/9781439821091","author":"bus?oniu","year":"2010","journal-title":"Reinforcement Learning and Dynamic Programming Using Function Approximators"}],"event":{"name":"2012 IEEE 51st Annual Conference on Decision and Control (CDC)","start":{"date-parts":[[2012,12,10]]},"location":"Maui, HI, USA","end":{"date-parts":[[2012,12,13]]}},"container-title":["2012 IEEE 51st IEEE Conference on Decision and Control (CDC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx5\/6416474\/6425800\/06426427.pdf?arnumber=6426427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,6,21]],"date-time":"2017-06-21T03:14:02Z","timestamp":1498014842000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/6426427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012,12]]},"references-count":12,"URL":"https:\/\/doi.org\/10.1109\/cdc.2012.6426427","relation":{},"subject":[],"published":{"date-parts":[[2012,12]]}}}