{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T15:12:20Z","timestamp":1784646740117,"version":"3.55.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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":["62373364"],"award-info":[{"award-number":["62373364"]}],"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":["62176259"],"award-info":[{"award-number":["62176259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013064","name":"Key Research and Development Program of Jiangsu Province","doi-asserted-by":"publisher","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}],"id":[{"id":"10.13039\/501100013064","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tsmc.2025.3583392","type":"journal-article","created":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T17:44:56Z","timestamp":1752255896000},"page":"7247-7258","source":"Crossref","is-referenced-by-count":3,"title":["PCDT: Pessimistic Critic Decision Transformer for Offline Reinforcement Learning"],"prefix":"10.1109","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8963-6374","authenticated-orcid":false,"given":"Jiazhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L.","family":"Philip Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2024.3449294"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2020.3000073"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3098451"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2021.3050960"},{"key":"ref6","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref7","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref8","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref9","article-title":"Decision ConvFormer: Local filtering in metaformer is sufficient for decision making","author":"Kim","year":"2023","journal-title":"arXiv:2310.03022"},{"key":"ref10","first-page":"27042","article-title":"Online decision transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zheng"},{"key":"ref11","article-title":"Elastic decision transformer","author":"Wu","year":"2023","journal-title":"arXiv:2307.02484"},{"key":"ref12","first-page":"38966","article-title":"You can\u2019t count on luck: Why decision transformers and RVS fail in stochastic environments","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paster"},{"key":"ref13","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kumar"},{"key":"ref14","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fujimoto"},{"key":"ref15","first-page":"3909","article-title":"Q-transformer: Scalable offline reinforcement learning via autoregressive q-functions","volume-title":"Proc. Conf. Robot Learn.","author":"Chebotar"},{"key":"ref16","article-title":"QT-TDM: Planning with transformer dynamics model and autoregressive Q-learning","author":"Kotb","year":"2024","journal-title":"arXiv:2407.18841"},{"key":"ref17","article-title":"Offline reinforcement learning with implicit Q-learning","author":"Kostrikov","year":"2021","journal-title":"arXiv:2110.06169"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2024.3388007"},{"key":"ref19","article-title":"Diffusion policies as an expressive policy class for offline reinforcement learning","author":"Wang","year":"2022","journal-title":"arXiv:2208.06193"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2024.3413308"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3297711"},{"key":"ref22","first-page":"38989","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline RL","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yamagata"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29499"},{"key":"ref24","article-title":"RVS: What is essential for offline RL via supervised learning?","author":"Emmons","year":"2021","journal-title":"arXiv:2112.10751"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tsmc.2024.3446841"},{"key":"ref26","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref27","first-page":"40587","article-title":"Supported value regularization for offline reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mao"},{"key":"ref28","article-title":"When do transformers shine in RL? Decoupling memory from credit assignment","author":"Ni","year":"2023","journal-title":"arXiv:2307.03864"},{"key":"ref29","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref30","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref31","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":"ref32","first-page":"1542","article-title":"When does return-conditioned supervised learning work for offline reinforcement learning?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brandfonbrener"},{"key":"ref33","article-title":"Iteratively refined behavior regularization for offline reinforcement learning","author":"Hu","year":"2023","journal-title":"arXiv:2306.05726"},{"key":"ref34","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref35","article-title":"Reinformer: Max-return sequence modeling for offline RL","author":"Zhuang","year":"2024","journal-title":"arXiv:2405.08740"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6221021\/11173422\/11078293.pdf?arnumber=11078293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:29:17Z","timestamp":1759235357000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11078293\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":35,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2025.3583392","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}