{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T16:46:02Z","timestamp":1779900362898,"version":"3.53.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Hong Kong Research Grant Council through the General Research Fund","award":["11216323"],"award-info":[{"award-number":["11216323"]}]},{"name":"Research Impact Fund","award":["R5060-19"],"award-info":[{"award-number":["R5060-19"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1109\/tnnls.2025.3557930","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T13:41:51Z","timestamp":1745329311000},"page":"16864-16878","source":"Crossref","is-referenced-by-count":4,"title":["A Two-Stage Selective Experience Replay for Double-Actor Deep Reinforcement Learning"],"prefix":"10.1109","volume":"36","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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiwei","family":"Fu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"AlignMamba: Enhancing multimodal mamba with local and global cross-modal alignment","author":"Li","year":"2024","journal-title":"arXiv:2412.00833"},{"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":"10.1007\/s10462-021-09997-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892603"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3594409.3594417"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3583131.3590455"},{"key":"ref9","article-title":"The in-sample softmax for offline reinforcement learning","author":"Xiao","year":"2023","journal-title":"arXiv:2302.14372"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.119494"},{"key":"ref11","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref12","first-page":"1365","article-title":"Regularized softmax deep multi-agent Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pan"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2024.3388470"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.10.085"},{"key":"ref16","article-title":"Simultaneous double Q-learning with conservative advantage learning for actor\u2013critic methods","author":"Li","year":"2022","journal-title":"arXiv:2205.03819"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3414472"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2023.3325843"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3390\/en15165878"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2024.3359911"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/math11010178"},{"key":"ref22","article-title":"Mitigating off-policy bias in actor\u2013critic methods with one-step Q-learning: A novel correction approach","volume":"1","author":"Saglam","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3385570"},{"key":"ref24","article-title":"RLx2: Training a sparse deep reinforcement learning model from scratch","author":"Tan","year":"2022","journal-title":"arXiv:2205.15043"},{"key":"ref25","first-page":"16828","article-title":"The primacy bias in deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nikishin"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3294187"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.08.025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.conengprac.2023.105462"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CBD63341.2023.00018"},{"key":"ref30","article-title":"MENTOR: Guiding hierarchical reinforcement learning with human feedback and dynamic distance constraint","author":"Zhou","year":"2024","journal-title":"arXiv:2402.14244"},{"key":"ref31","article-title":"Policy expansion for bridging offline-to-online reinforcement learning","author":"Zhang","year":"2023","journal-title":"arXiv:2302.00935"},{"key":"ref32","article-title":"Offline actor\u2013critic reinforcement learning scales to large models","author":"Tobias Springenberg","year":"2024","journal-title":"arXiv:2402.05546"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3359039"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.14819"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI52525.2021.00199"},{"key":"ref36","article-title":"Prioritized experience replay","author":"Schaul","year":"2015","journal-title":"arXiv:1511.05952"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/365"},{"key":"ref38","first-page":"1","article-title":"Synthetic experience replay","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-024-09913-6"},{"key":"ref40","first-page":"1751","article-title":"Selective experience replay compression using coresets for lifelong deep reinforcement learning in medical imaging","volume-title":"Proc. Med. Imag. Deep Learn.","author":"Zheng"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11595"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108875"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-023-01981-9"},{"key":"ref44","article-title":"Local cluster experience replay","author":"Zahlner","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.02.004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2588"},{"key":"ref47","article-title":"Cluster-based sampling in hindsight experience replay for robot control","author":"Kim","year":"2022","journal-title":"arXiv:2208.14741"},{"key":"ref48","article-title":"Continual reinforcement learning with multi-timescale replay","author":"Kaplanis","year":"2020","journal-title":"arXiv:2004.07530"},{"key":"ref49","first-page":"2159","article-title":"Deterministic policy gradient: Convergence analysis","volume-title":"Proc. Uncertainty Artif. Intell.","author":"Xiong"},{"key":"ref50","first-page":"28701","article-title":"Policy regularization with dataset constraint for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ran"},{"key":"ref51","first-page":"1","article-title":"Iteratively refined behavior regularization for offline reinforcement learning","volume-title":"Proc. 38th Conf. Neural Inf. Process. Syst.","author":"Hu"},{"key":"ref52","article-title":"CrossQ: Batch normalization in deep reinforcement learning for greater sample efficiency and simplicity","author":"Bhatt","year":"2019","journal-title":"arXiv:1902.05605"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3368055"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3446996"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3170485"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3449294"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00012"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI52525.2021.00027"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11151745\/10973161.pdf?arnumber=10973161","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T18:25:29Z","timestamp":1757096729000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10973161\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":58,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2025.3557930","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}