{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:00:08Z","timestamp":1766066408616},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2015,10,1]],"date-time":"2015-10-01T00:00:00Z","timestamp":1443657600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2015,10]]},"DOI":"10.1109\/tnnls.2014.2378812","type":"journal-article","created":{"date-parts":[[2015,1,8]],"date-time":"2015-01-08T19:39:04Z","timestamp":1420745944000},"page":"2301-2310","source":"Crossref","is-referenced-by-count":41,"title":["Optimal Critic Learning for Robot Control in Time-Varying Environments"],"prefix":"10.1109","volume":"26","author":[{"given":"Chen","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yanan","family":"Li","sequence":"additional","affiliation":[]},{"given":"Shuzhi Sam","family":"Ge","sequence":"additional","affiliation":[]},{"given":"Tong Heng","family":"Lee","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1007\/BF00992698","article-title":"Q-learning","volume":"8","author":"watkins","year":"2009","journal-title":"Machine Learning"},{"key":"ref38","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198537953.001.0001","author":"lancaster","year":"1995","journal-title":"Algebraic Riccati Equations"},{"key":"ref33","doi-asserted-by":"crossref","DOI":"10.1142\/3774","author":"ge","year":"1998","journal-title":"Adaptive Neural Network Control of Robotic Manipulators"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1177\/027836498700600303"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/S0094-114X(02)00045-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-6272-8_6"},{"key":"ref37","article-title":"Reinforcement learning and distributed local model synthesis","author":"landelius","year":"1997"},{"key":"ref36","article-title":"Learning and sequential decision making","author":"barto","year":"1989","journal-title":"Learning and Computational Neuroscience"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(90)90088-3"},{"key":"ref34","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1007\/978-3-642-28572-1_23","article-title":"Interaction force, impedance and trajectory adaptation: By humans, for robots","author":"burdet","year":"2014","journal-title":"Experimental Robotics"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2005.852261"},{"key":"ref40","author":"astrom","year":"1989","journal-title":"Adaptive Control"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.008"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2009.07.025"},{"key":"ref13","first-page":"67","article-title":"A menu of designs for reinforcement learning over time","author":"werbos","year":"1990","journal-title":"Neural Networks for Control"},{"key":"ref14","volume":"1","author":"bertsekas","year":"1995","journal-title":"Dynamic Programming and Optimal Control"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.03.012"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2010.2076370"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.918073"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.924139"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/70.88148"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2013.2286194"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CDC.1984.272176"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2011.642309"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/00207179.2013.827799"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/3477.485879"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2011.2158251"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1177\/0278364905056347"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.351417"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1115\/1.3140702"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1995.525537"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CMPSAC.1979.762539"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2009.2027233"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MCAS.2009.933854"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1109\/TNN.2007.905839","article-title":"Integrating temporal difference methods and self-organizing neural networks for reinforcement learning with delayed evaluative feedback","volume":"19","author":"tan","year":"2008","journal-title":"IEEE Trans Neural Netw"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta:20070096"},{"key":"ref24","volume":"17","author":"lewis","year":"2013","journal-title":"Reinforcement Learning and Approximate Dynamic Programming for Feedback Control"},{"key":"ref41","first-page":"4167","article-title":"Adaptive estimation of time-varying parameters in linear systems","volume":"5","author":"zhu","year":"2003","journal-title":"Proc Amer Control Conf"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MCS.2012.2214134"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/9.871761"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911402527"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(96)85559-2"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"433","DOI":"10.1109\/TSMCB.2009.2026289","article-title":"Impedance learning for robotic contact tasks using natural actor-critic algorithm","volume":"40","author":"kim","year":"2010","journal-title":"IEEE Trans Syst Man Cybern B Cybern"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/7287875\/07004793.pdf?arnumber=7004793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T12:53:20Z","timestamp":1717678400000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7004793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,10]]},"references-count":44,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2014.2378812","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,10]]}}}