{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T08:28:34Z","timestamp":1760171314471,"version":"3.44.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"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":["62073160"],"award-info":[{"award-number":["62073160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tai.2023.3316637","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T14:34:38Z","timestamp":1695134078000},"page":"2253-2263","source":"Crossref","is-referenced-by-count":2,"title":["Incremental Reinforcement Learning via Performance Evaluation and Policy Perturbation"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6589-4402","authenticated-orcid":false,"given":"Guizhou","family":"Deng","sequence":"first","affiliation":[{"name":"Mechanical Engineering, School of Manufacturing Science and Engineering, Southwest University of Science and Technology, Mianyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9403-2449","authenticated-orcid":false,"given":"Huiqiao","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Control and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3031-0056","authenticated-orcid":false,"given":"Xinpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Mechanical Engineering, School of Manufacturing Science and Engineering, Southwest University of Science and Technology, Mianyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4890-1825","authenticated-orcid":false,"given":"Canghai","family":"Liu","sequence":"additional","affiliation":[{"name":"Mechanical Engineering, School of Manufacturing Science and Engineering, Southwest University of Science and Technology, Mianyang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7456-0962","authenticated-orcid":false,"given":"Kaiqiang","family":"Tang","sequence":"additional","affiliation":[{"name":"Department of Control and Systems Engineering, School of Management and Engineering, 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 and Systems Engineering, School of Management and Engineering, Nanjing University, Nanjing, China"}]}],"member":"263","reference":[{"volume-title":"Reinforcement Learning: An Introduction.","year":"2018","author":"Sutton","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/science.153.3731.34"},{"key":"ref3","first-page":"1068","article-title":"On-line policy improvement using Monte-Carlo search","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tesauro","year":"1997"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3237665"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3127857"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2021.3072675"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061372"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3059676"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979660"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/328"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3061073"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2988277"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2021.3120837"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMECH.2019.2899365"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2019.1911390"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927320"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3055499"},{"key":"ref27","first-page":"1","article-title":"Guided policy search","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Levine","year":"2013"},{"key":"ref28","first-page":"80","article-title":"Eligibility traces for off-policy policy evaluation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Precup","year":"2000"},{"article-title":"Parameter space noise for exploration","year":"2017","author":"Plappert","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/10187.001.0001"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref32","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan","year":"2016"},{"key":"ref33","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton","year":"2000"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref35","first-page":"4936","article-title":"Importance weighted transfer of samples in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tirinzoni","year":"2018"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2543238"},{"key":"ref37","first-page":"2063","article-title":"Transfer learning for related reinforcement learning tasks via image-to-image translation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gamrian","year":"2019"},{"key":"ref38","first-page":"3981","article-title":"Learning to learn by gradient descent by gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2016"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3028378"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160173"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2791511"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2018.2874465"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0075-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2018.2810447"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911426178"},{"key":"ref46","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3175656"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10532210\/10255268.pdf?arnumber=10255268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:07Z","timestamp":1755911347000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10255268\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":48,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tai.2023.3316637","relation":{},"ISSN":["2691-4581"],"issn-type":[{"type":"electronic","value":"2691-4581"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}