{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T16:23:52Z","timestamp":1783873432226,"version":"3.55.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0119903"],"award-info":[{"award-number":["2022ZD0119903"]}],"id":[{"id":"10.13039\/501100012166","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":["ZDYF2021GXJS041"],"award-info":[{"award-number":["ZDYF2021GXJS041"]}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tnnls.2023.3309906","type":"journal-article","created":{"date-parts":[[2023,9,7]],"date-time":"2023-09-07T17:35:58Z","timestamp":1694108158000},"page":"17950-17964","source":"Crossref","is-referenced-by-count":10,"title":["Mild Policy Evaluation for Offline Actor\u2013Critic"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"first","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2026-6856","authenticated-orcid":false,"given":"Botao","family":"Dong","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinhui","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Ship and Shipping Research Institute Company Ltd., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4700-1276","authenticated-orcid":false,"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3202192"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11694"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3116063"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2019.2955905"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnsre.2022.3196468"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3084374"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2022.3209290"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3359554"},{"key":"ref10","first-page":"2307","article-title":"Offline reinforcement learning with pseudometric learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dadashi"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref12","first-page":"15621","article-title":"Nearly horizon-free offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref13","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2959129"},{"key":"ref15","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref16","first-page":"11784","article-title":"Stabilizing off policy Q learning via bootstrapping error reduction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref17","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref18","article-title":"Batch reinforcement learning through continuation method","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guo"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2015.2504100"},{"key":"ref20","first-page":"1179","article-title":"Conservative Q learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref21","first-page":"11319","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref22","first-page":"5774","article-title":"Offline reinforcement learning with Fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/foundations1020018"},{"key":"ref24","article-title":"Density estimation for conservative Q-learning","volume-title":"Proc. ICLR Workshop Generalizable Policy Learn. Phys. World","author":"Daoudi"},{"key":"ref25","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref26","first-page":"19235","article-title":"Conservative offline distributional reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3217189"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20855"},{"key":"ref29","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref30","first-page":"568","article-title":"Error propagation for approximate policy and value iteration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Farahmand"},{"key":"ref31","first-page":"23645","article-title":"Koopman Q-learning: Offline reinforcement learning via symmetries of dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Weissenbacher"},{"key":"ref32","first-page":"4933","article-title":"Offline RL without off-policy evaluation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brandfonbrener"},{"key":"ref33","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kostrikov"},{"key":"ref34","first-page":"1543","article-title":"You only evaluate once: A simple baseline algorithm for offline RL","volume-title":"Proc. Conf. Robot Learn.","author":"Goo"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref36","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref37","article-title":"When data geometry meets deep function: Generalizing offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3230064"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127492"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01630"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10772360\/10243452.pdf?arnumber=10243452","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T19:11:08Z","timestamp":1733253068000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10243452\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":40,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2023.3309906","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}