{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:53:56Z","timestamp":1775854436508,"version":"3.50.1"},"reference-count":43,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0119900"],"award-info":[{"award-number":["2022ZD0119900"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Science and Technology Program","award":["22015810300"],"award-info":[{"award-number":["22015810300"]}]},{"name":"Hainan Province Science and Technology Special Fund","award":["ZDYF2024GXJS003"],"award-info":[{"award-number":["ZDYF2024GXJS003"]}]},{"name":"Shanghai Pujiang Program","award":["23PJ1404700"],"award-info":[{"award-number":["23PJ1404700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U2141234"],"award-info":[{"award-number":["U2141234"]}],"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":["U24A20260"],"award-info":[{"award-number":["U24A20260"]}],"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":["62303308"],"award-info":[{"award-number":["62303308"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tcds.2025.3611975","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T17:46:14Z","timestamp":1758563174000},"page":"504-517","source":"Crossref","is-referenced-by-count":1,"title":["Sarsa-Augmented Off-Policy Reinforcement Learning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4322-4314","authenticated-orcid":false,"given":"Ning","family":"Pang","sequence":"first","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-6856","authenticated-orcid":false,"given":"Botao","family":"Dong","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-9668","authenticated-orcid":false,"given":"Hongtian","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2070-960X","authenticated-orcid":false,"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Electronic and Information Engineering, Southwest University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4700-1276","authenticated-orcid":false,"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Automation and Intelligent Sensing, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Reinforcement Learning and Optimal Control.","author":"Bertsekas","year":"2019"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2019.2924724"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3265200"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3326867"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3092715"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2022.3207575"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3269396"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3089941"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1287\/opre.2022.2382"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2609500"},{"key":"ref11","first-page":"5437","article-title":"Off-policy evaluation via off-policy classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Irpan","year":"2019"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref13","first-page":"121","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Lillicrap","year":"2016"},{"key":"ref14","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Fujimoto","year":"2018"},{"key":"ref15","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20732"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16973"},{"key":"ref18","article-title":"Mitigating estimation errors by twin TD-regularized actor and critic for deep reinforcement learning","author":"Zhong","year":"2023"},{"key":"ref19","first-page":"145","article-title":"Count-based temperature scheduling for maximum entropy reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst","author":"Hu","year":"2021"},{"key":"ref20","first-page":"27537","article-title":"CUP: Critic-guided policy reuse","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"35","author":"Zhang","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3034452"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3329513"},{"key":"ref23","first-page":"11767","article-title":"Softmax deep double deterministic policy gradients","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"33","author":"Pan","year":"2020"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1109\/CDC49753.2023.10383469","article-title":"Conformal off-policy evaluation in Markov decision processes","author":"Foffano","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3364844"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43421-1_27"},{"key":"ref27","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":"ref28","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Fujimoto","year":"2019"},{"key":"ref29","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume":"32","author":"Kumar","year":"2019","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref30","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"33","author":"Wang","year":"2020"},{"key":"ref31","article-title":"The importance of pessimism in fixed-dataset policy optimization","author":"Buckman","year":"2020","journal-title":"Proc. Int. Conf. Learn. Represent"},{"key":"ref32","volume-title":"On-Line Q-Learning Using Connectionist System.","author":"Rummery","year":"1994"},{"key":"ref33","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Schulman"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref35","article-title":"CPPO: Continual learning for reinforcement learning with human feedback","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Zhang","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3051456"},{"key":"ref37","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Haarnoja"},{"key":"ref38","first-page":"4026","article-title":"Stochastic variance-reduced policy gradient","volume-title":"Proc. Int. Conf. Mach. Learn","author":"Papini","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3481887"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5932"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3538879"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2023.3246985"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2649564"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11477821\/11174994.pdf?arnumber=11174994","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T20:00:56Z","timestamp":1775851256000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11174994\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":43,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3611975","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"value":"2379-8920","type":"print"},{"value":"2379-8939","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}