{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T01:56:34Z","timestamp":1769306194737,"version":"3.49.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2016,7,1]],"date-time":"2016-07-01T00:00:00Z","timestamp":1467331200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Coordena\u00e7\u00e3o de Aperfei\u00e7oamento de Pessoal de Nivel Superior through the Science without Borders Program\u2013Ci\u00eancia sem Fronteiras"},{"DOI":"10.13039\/501100000780","name":"European Union through the Seventh Framework Program","doi-asserted-by":"publisher","award":["611909"],"award-info":[{"award-number":["611909"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2016,7]]},"DOI":"10.1109\/tnnls.2015.2442233","type":"journal-article","created":{"date-parts":[[2015,6,23]],"date-time":"2015-06-23T14:51:09Z","timestamp":1435071069000},"page":"1457-1468","source":"Crossref","is-referenced-by-count":13,"title":["Parallel Online Temporal Difference Learning for Motor Control"],"prefix":"10.1109","volume":"27","author":[{"given":"Wouter","family":"Caarls","sequence":"first","affiliation":[]},{"given":"Erik","family":"Schuitema","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"ref38","first-page":"317","article-title":"Neural fitted Q iteration—First experiences with a data efficient neural reinforcement learning method","author":"riedmiller","year":"2005","journal-title":"Proc 16th Eur Conf Mach Learn"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/293347.293348"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2001.932842"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006559212014"},{"key":"ref37","first-page":"503","article-title":"Tree-based batch mode reinforcement learning","volume":"6","author":"ernst","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref35","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","author":"deisenroth","year":"2011","journal-title":"Proc 28th Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317250933"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2002.1014237"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2011.2170565"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2007.363631"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-009-9120-4"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2014.6889733"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642157"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5322-7"},{"key":"ref28","first-page":"1","article-title":"Dyna-style planning with linear function approximation and prioritized sweeping","author":"sutton","year":"2008","journal-title":"Proc 24th Conf Uncertainty Artif Intell"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.2478\/pjbr-2013-0003"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00993104"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_18"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1095408.1095418"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI.2004.28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2005.1570760"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(01)00113-0"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2010.5650765"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/S0921-8890(97)00043-2"},{"key":"ref1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696351"},{"key":"ref20","first-page":"1","article-title":"Reinforcement learning algorithms for homogenous multi-agent systems","author":"kretchmar","year":"2003","journal-title":"Proc Workshop Agent Swarm Program"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-012-5280-0"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SICE.2007.4421460"},{"key":"ref21","first-page":"761","article-title":"Horde: A scalable real-time architecture for learning knowledge from unsupervised sensorimotor interaction","author":"sutton","year":"2011","journal-title":"Proc 10th Int Conf Auton Agents Multiagent Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1201\/9781439821091"},{"key":"ref24","first-page":"309","article-title":"MapReduce for parallel reinforcement learning","author":"li","year":"2011","journal-title":"Proc of European Workshop on Reinforcement Learning"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ADPRL.2009.4927542"},{"key":"ref23","article-title":"Scaling reinforcement learning to the unconstrained multi-agent domain","author":"palmer","year":"2007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1115\/1.3426922"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CCA.2001.973983"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390240"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/7492215\/07131566.pdf?arnumber=7131566","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:45:28Z","timestamp":1641987928000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7131566\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,7]]},"references-count":46,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2015.2442233","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,7]]}}}