{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:14:45Z","timestamp":1771467285515,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006111"],"award-info":[{"award-number":["62006111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council\u2019s Future Fellowship funding scheme","doi-asserted-by":"publisher","award":["FT220100656"],"award-info":[{"award-number":["FT220100656"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Natural Science Foundation of Jiangsu Province of China","doi-asserted-by":"publisher","award":["BK20200330"],"award-info":[{"award-number":["BK20200330"]}],"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":[[2024,10]]},"DOI":"10.1109\/tnnls.2023.3281604","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T17:19:34Z","timestamp":1686676774000},"page":"14797-14809","source":"Crossref","is-referenced-by-count":3,"title":["Efficient Bayesian Policy Reuse With a Scalable Observation Model in Deep Reinforcement Learning"],"prefix":"10.1109","volume":"35","author":[{"given":"Jinmei","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0304-3965","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3929-4707","authenticated-orcid":false,"given":"Chunlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Control Science and Intelligent Engineering, School of Management and Engineering, and the Research Center for Novel Technology of Intelligent Equipment, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-3559","authenticated-orcid":false,"given":"Daoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Engineering and Information Technology, University of New South Wales, Canberra, ACT, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3072571"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3098985"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/rnc.5341"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-8387-7_134"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3053414"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3142822"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41562-019-0804-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref16","first-page":"6651","article-title":"Evolutionary reinforcement learning for sample-efficient multiagent coordination","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"119","author":"Majumdar"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"key":"ref18","first-page":"7780","article-title":"Offline meta-reinforcement learning with advantage weighting","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Mitchell"},{"issue":"7","key":"ref19","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":"ref20","first-page":"15146","article-title":"Knowledge transfer in multitask deep reinforcement learning for continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Xu"},{"key":"ref21","first-page":"1","article-title":"A new representation of successor features for transfer across dissimilar environments","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Abdolshah"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref23","article-title":"Learning invariant feature spaces to transfer skills with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gupta"},{"key":"ref24","article-title":"Actor-mimic: Deep multitask and transfer reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Parisotto"},{"key":"ref25","article-title":"Single episode policy transfer in reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref26","first-page":"4058","article-title":"Successor features for transfer in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Barreto"},{"key":"ref27","first-page":"181","article-title":"Policy transfer using reward shaping","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Brys"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9562051"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-016-5547-y"},{"key":"ref30","first-page":"1315","article-title":"A Bayesian approach for learning and tracking switching, non-stationary opponents","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Hernandez-Leal"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/88"},{"key":"ref32","first-page":"962","article-title":"A deep Bayesian policy reuse approach against non-stationary agents","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Zheng"},{"key":"ref33","article-title":"A Bayesian policy reuse approach for bilateral negotiation games","volume-title":"Proc. AAAI Conf. Artif. Intell., Workshop Reinforcement Learn. Games","author":"Gao"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-020-09480-9"},{"key":"ref35","first-page":"10141","article-title":"Repaint: Knowledge transfer in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Tao"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390225"},{"key":"ref37","first-page":"468","article-title":"Measuring the distance between finite Markov decision processes","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Song"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10796"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1002\/acs.3326"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2010.03.007"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11718"},{"key":"ref42","first-page":"989","article-title":"Context-aware policy reuse","volume-title":"Proc. Int. Conf. Auto. Agents Multiagent Syst.","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/428"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065704001899"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3004171"},{"key":"ref47","article-title":"Gaussian processes in reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"4","author":"Rasmussen"},{"key":"ref48","first-page":"465","article-title":"PILCO: A model-based and data-efficient approach to policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deisenroth"},{"key":"ref49","first-page":"1432","article-title":"Hidden parameter Markov decision processes: A semiparametric regression approach for discovering latent task parametrizations","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Doshi-Velez"},{"key":"ref50","first-page":"909","article-title":"Safe model-based reinforcement learning with stability guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"2","author":"Berkenkamp"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927320"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/37.236324"},{"key":"ref53","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref55","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref56","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref58","article-title":"Efficient approaches to Gaussian process classification","volume":"12","author":"Csat\u00f3","year":"1999","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1162\/089976602317250933"},{"key":"ref60","article-title":"Fast sparse Gaussian process methods: The informative vector machine","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"15","author":"Lawrence"},{"key":"ref61","first-page":"211","article-title":"Sparse Bayesian learning and the relevance vector machine","volume":"1","author":"Tipping","year":"2001","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10707065\/10149182.pdf?arnumber=10149182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,11]],"date-time":"2024-12-11T01:50:50Z","timestamp":1733881850000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10149182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":61,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3281604","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}