{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T02:13:41Z","timestamp":1778552021692,"version":"3.51.4"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grants Council"},{"name":"General Research Fund","award":["11219624"],"award-info":[{"award-number":["11219624"]}]},{"name":"Collaborative Research Fund","award":["C1045-23G"],"award-info":[{"award-number":["C1045-23G"]}]},{"name":"National Key Research and Development Program of China","award":["2023YFF0615802"],"award-info":[{"award-number":["2023YFF0615802"]}]},{"name":"Key R&D Program of Jiangxi Province","award":["20243BBG71033"],"award-info":[{"award-number":["20243BBG71033"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tpami.2026.3664855","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:06:50Z","timestamp":1771276010000},"page":"7112-7128","source":"Crossref","is-referenced-by-count":0,"title":["A Generic Competitive-Cooperative Actor-Critic Framework for Deep Reinforcement Learning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4857-5439","authenticated-orcid":false,"given":"Meng","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5401-5393","authenticated-orcid":false,"given":"Zihao","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8563-148X","authenticated-orcid":false,"given":"Xinhong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanyi","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8774-2936","authenticated-orcid":false,"given":"Jin","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Vehicle and Mobility, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9318-1482","authenticated-orcid":false,"given":"Jianping","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02307"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3672398"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3440924"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3581217"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2025.3537990"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3557930"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3642900"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892603"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3594409.3594417"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590455"},{"key":"ref12","article-title":"The in-sample softmax for offline reinforcement learning","author":"Xiao","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119494"},{"key":"ref14","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","year":"2020"},{"key":"ref15","first-page":"1365","article-title":"Regularized softmax deep multi-agent Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3388470"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.085"},{"key":"ref19","article-title":"Simultaneous double Q-learning with conservative advantage learning for actor-critic methods","author":"Li","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/en15165878"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3359911"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3414472"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3325843"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/math11010178"},{"key":"ref25","first-page":"16828","article-title":"The primacy bias in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nikishin","year":"2022"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11063-024-11461-y"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"issue":"152","key":"ref28","first-page":"1","article-title":"Intrinsically motivated goal exploration processes with automatic curriculum learning","volume":"23","author":"Forestier","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.13554"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3368055"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI52525.2021.00027"},{"key":"ref32","first-page":"40531","article-title":"Automatic intrinsic reward shaping for exploration in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yuan","year":"2023"},{"key":"ref33","first-page":"17662","article-title":"Online meta-critic learning for off-policy actor-critic methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou","year":"2020"},{"key":"ref34","article-title":"AWAC: Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126628"},{"key":"ref36","first-page":"3230","article-title":"Byzantine-robust online and offline distributed reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Chen","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.20517\/ir.2021.02"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.65109\/PJZX8047"},{"key":"ref39","first-page":"5223","article-title":"Keep various trajectories: Promoting exploration of ensemble policies in continuous control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li","year":"2024"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1631\/1\/012040"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00132"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412614"},{"key":"ref43","article-title":"Remember and forget experience replay for multi-agent reinforcement learning","author":"Weber","year":"2022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3170485"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2099"},{"key":"ref46","first-page":"6334","article-title":"Provable lifelong learning of representations","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Cao","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29165"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.02.027"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3299556"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3056373"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/e26010093"},{"key":"ref52","article-title":"Maxmin Q-learning: Controlling the estimation bias of Q-learning","author":"Lan","year":"2020"},{"key":"ref53","first-page":"6131","article-title":"SUNRISE: A simple unified framework for ensemble learning in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2021"},{"key":"ref54","article-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021"},{"key":"ref55","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto","year":"2021"},{"key":"ref56","first-page":"39509","article-title":"Boosting offline reinforcement learning with action preference query","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3671127.3698163"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3401014"},{"key":"ref59","first-page":"2835","article-title":"Mitigating off-policy bias in actor-critic methods with one-step Q-learning: A novel correction approach","volume":"2024","author":"Saglam","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3385570"},{"key":"ref61","first-page":"441","article-title":"Reactive exploration to cope with non-stationarity in lifelong reinforcement learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Steinparz","year":"2022"},{"key":"ref62","first-page":"838","article-title":"Lifelong robotic reinforcement learning by retaining experiences","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Xie","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802060"},{"key":"ref64","first-page":"1","article-title":"UNCLEAR: A straightforward method for continual reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Kessler","year":"2020"},{"key":"ref65","first-page":"5556","article-title":"Controlling overestimation bias with truncated mixture of continuous distributional quantile critics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kuznetsov","year":"2020"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2023.123477"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3280085"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3160173"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11512030\/11397214.pdf?arnumber=11397214","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:52:40Z","timestamp":1778550760000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397214\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":68,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3664855","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}