{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T20:45:17Z","timestamp":1761597917386,"version":"3.37.3"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2018,6,1]],"date-time":"2018-06-01T00:00:00Z","timestamp":1527811200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["61751306"],"award-info":[{"award-number":["61751306"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Jiangsu Science Foundation","doi-asserted-by":"publisher","award":["BK20170013"],"award-info":[{"award-number":["BK20170013"]}],"id":[{"id":"10.13039\/501100004608","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":[[2018,6]]},"DOI":"10.1109\/tnnls.2018.2803729","type":"journal-article","created":{"date-parts":[[2018,3,6]],"date-time":"2018-03-06T19:16:44Z","timestamp":1520363804000},"page":"2204-2215","source":"Crossref","is-referenced-by-count":13,"title":["Reusable Reinforcement Learning via Shallow Trails"],"prefix":"10.1109","volume":"29","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1732-9545","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6417-1912","authenticated-orcid":false,"given":"Shi-Yong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qing","family":"Da","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0746-1494","authenticated-orcid":false,"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Distance dependent Chinese restaurant processes","author":"blei","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.01.039"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2014.6907421"},{"key":"ref32","first-page":"1","article-title":"Sim-to-real robot learning from pixels with progressive nets","author":"rusu","year":"2017","journal-title":"Proc 1st Conf Robot Learn"},{"key":"ref31","first-page":"1131","article-title":"Multi-task reinforcement learning in partially observable stochastic environments","volume":"10","author":"li","year":"2009","journal-title":"J Mach Learn Res"},{"key":"ref30","first-page":"3320","article-title":"How transferable are features in deep neural networks?","author":"yosinski","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref37","first-page":"269","article-title":"A survey of clustering algorithms","author":"rokach","year":"2010","journal-title":"Data Mining and Knowledge Discovery Handbook"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-015-5470-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1968.1972"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/SERA.2005.55"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/BRACIS.2016.027"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref11","first-page":"599","article-title":"Bayesian multi-task reinforcement learning","author":"lazaric","year":"2010","journal-title":"Proc 27th Int Conf Mach Learn (ICML)"},{"key":"ref12","article-title":"Multi-task learning with deep model based reinforcement learning","author":"mujika","year":"2016","journal-title":"CoRR"},{"key":"ref13","first-page":"242","article-title":"Transfer learning","volume":"1","author":"torrey","year":"2009","journal-title":"Handbook Of Research On Machine Learning Applications and Trends Algorithms Methods and Techniques"},{"key":"ref14","first-page":"1","article-title":"Learning parameterized skills","author":"da silva","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn (ICML)"},{"key":"ref15","first-page":"1","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-5038-5"},{"key":"ref17","first-page":"213","article-title":"R-MAX—A general polynomial time algorithm for near-optimal reinforcement learning","volume":"3","author":"brafman","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-73580-9_21"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1613\/jair.806","article-title":"Infinite-horizon policy-gradient estimation","volume":"15","author":"baxter","year":"2001","journal-title":"J Artif Intell Res"},{"key":"ref28","first-page":"1041","article-title":"Transfer learning in real-time strategy games using hybrid CBR\/RL","author":"sharma","year":"2007","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-87481-2_32"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/1160633.1160762"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-016-6906-3"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5061-y"},{"key":"ref7","first-page":"1746","article-title":"Transfer from multiple MDPs","author":"lazaric","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst 24"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwx106"},{"key":"ref9","article-title":"Actor-Mimic: Deep multitask and transfer reinforcement learning","author":"parisotto","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)ICLR"},{"journal-title":"Reinforcement Learning An Introduction","year":"1998","author":"sutton","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref22","first-page":"1","article-title":"Sequential classification-based optimization for direct policy search","author":"hu","year":"2017","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390214"},{"key":"ref42","first-page":"1","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc 33nd Int Conf Mach Learn (ICML)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"key":"ref41","article-title":"Sim-to-real transfer of robotic control with dynamics randomization","author":"peng","year":"2017","journal-title":"CoRR"},{"key":"ref23","first-page":"1058","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref25","first-page":"1946","article-title":"Derivative-free optimization of high-dimensional non-convex functions by sequential random embeddings","author":"qian","year":"2016","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/8360119\/08307260.pdf?arnumber=8307260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:12:34Z","timestamp":1642003954000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8307260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,6]]},"references-count":43,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2018.2803729","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2018,6]]}}}