{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T02:59:13Z","timestamp":1775789953872,"version":"3.50.1"},"reference-count":36,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,3,1]],"date-time":"2019-03-01T00:00:00Z","timestamp":1551398400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["169"],"award-info":[{"award-number":["169"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1109\/tcds.2017.2718938","type":"journal-article","created":{"date-parts":[[2017,6,22]],"date-time":"2017-06-22T18:50:03Z","timestamp":1498157403000},"page":"26-35","source":"Crossref","is-referenced-by-count":31,"title":["Combining Model-Based $Q$ -Learning With Structural Knowledge Transfer for Robot Skill Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0240-0919","authenticated-orcid":false,"given":"Zhen","family":"Deng","sequence":"first","affiliation":[]},{"given":"Haojun","family":"Guan","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Hongzhuo","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Liwei","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jianwei","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2543839"},{"key":"ref32","first-page":"319","article-title":"Learning human compliant behavior from demonstration for force-based robot manipulation","author":"deng","year":"2016","journal-title":"Proc IEEE Int Conf Robot Biomimetics (RoBio)"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1177\/0278364904048962"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2016.2614675"},{"key":"ref36","doi-asserted-by":"crossref","first-page":"425","DOI":"10.1016\/S0079-6123(06)65027-9","article-title":"Dynamics systems vs. optimal control—A unifying view","volume":"165","author":"schaal","year":"2007","journal-title":"Progr Brain Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015430"},{"key":"ref34","first-page":"1000","article-title":"Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance","volume":"6","author":"thomaz","year":"2006","journal-title":"Proc AAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1162\/089976602753712972"},{"key":"ref11","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 (ICML)"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"1401","DOI":"10.1609\/aaai.v27i1.8546","article-title":"Data-efficient generalization of robot skills with contextual policy search","author":"kupcsik","year":"2013","journal-title":"Proc AAAI"},{"key":"ref13","first-page":"1","article-title":"Guided policy search","volume":"3","author":"levine","year":"2013","journal-title":"Proc ICML"},{"key":"ref14","first-page":"273","article-title":"Hierarchical relative entropy policy search","author":"daniel","year":"2012","journal-title":"Proc AISTATS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1177\/0278364912472380"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5547-y"},{"key":"ref17","first-page":"1633","article-title":"Transfer learning for reinforcement learning domains: A survey","volume":"10","author":"taylor","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref18","article-title":"A reinforcement learning architecture that transfers knowledge between skills when solving multiple tasks","author":"tommasino","year":"0","journal-title":"IEEE Trans Cogn Develop Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907423"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759417"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2014.11.005"},{"key":"ref27","first-page":"1341","article-title":"Gaussian process training with input noise","volume":"24","author":"mchutchon","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-005-5732-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2008.10.024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2012.05.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138994"},{"key":"ref7","first-page":"849","article-title":"Policy search for motor primitives in robotics","author":"kober","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref1","volume":"1","author":"sutton","year":"1998","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref20","first-page":"2125","article-title":"Transfer learning via inter-task mappings for temporal difference learning","volume":"8","author":"taylor","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref22","first-page":"1547","article-title":"Learning attractor landscapes for learning motor primitives","author":"ijspeert","year":"2003","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139550"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2009.5152577"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2010.5686298"},{"key":"ref26","first-page":"57","article-title":"Sparse convolved Gaussian processes for multi-output regression","author":"alvarez","year":"2009","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref25","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/8663462\/07955051.pdf?arnumber=7955051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T23:39:41Z","timestamp":1659137981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/7955051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,3]]},"references-count":36,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2017.2718938","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,3]]}}}