{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:06:03Z","timestamp":1785953163900,"version":"3.56.0"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"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":["62176259"],"award-info":[{"award-number":["62176259"]}],"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":["62373364"],"award-info":[{"award-number":["62373364"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Artif. Intell."],"published-print":{"date-parts":[[2024,8]]},"DOI":"10.1109\/tai.2024.3354694","type":"journal-article","created":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T13:38:46Z","timestamp":1705498726000},"page":"3915-3925","source":"Crossref","is-referenced-by-count":17,"title":["Proximal Policy Optimization With Advantage Reuse Competition"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1847-869X","authenticated-orcid":false,"given":"Qingbang","family":"Guo","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"2","key":"ref1","first-page":"229","article-title":"Reinforcement learning: An introduction","volume":"17","author":"Sutton","year":"1999","journal-title":"Robotica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5728"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3223892"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3309906"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3222143"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487517"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3097313"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/BigDIA53151.2021.9619637"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3184656"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3236897"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2923702"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3237665"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2022.3201807"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17326"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2004.1307456"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schulman","year":"2015"},{"key":"ref18","first-page":"1531","article-title":"A natural policy gradient","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"14","author":"Kakade","year":"2001"},{"key":"ref19","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560856"},{"key":"ref22","first-page":"11909","article-title":"Generalized proximal policy optimization with sample reuse","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Queeney","year":"2021"},{"key":"ref23","first-page":"22","article-title":"Constrained policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Achiam","year":"2017"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3051456"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9078688\/10635096\/10402062.pdf?arnumber=10402062","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:12Z","timestamp":1755911352000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10402062\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8]]},"references-count":24,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3354694","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8]]}}}