{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:17:31Z","timestamp":1759331851351,"version":"3.37.3"},"reference-count":57,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Xiaomi Young Talents Program"},{"name":"the Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab Project;"},{"name":"the Shanghai Municipal Science and Technology Major Project","award":["2018SHZDZX01"],"award-info":[{"award-number":["2018SHZDZX01"]}]},{"name":"ZJ Lab;"},{"DOI":"10.13039\/100020441","name":"Shanghai Center for Brain Science and Brain-Inspired Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020441","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Rising Star Program","award":["21QC1400900"],"award-info":[{"award-number":["21QC1400900"]}]},{"name":"Key Technologies Development and Application of Piloted Autonomous Driving Truck Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tcds.2023.3287987","type":"journal-article","created":{"date-parts":[[2023,6,20]],"date-time":"2023-06-20T17:36:05Z","timestamp":1687282565000},"page":"671-680","source":"Crossref","is-referenced-by-count":5,"title":["UAC: Offline Reinforcement Learning With Uncertain Action Constraint"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4097-438X","authenticated-orcid":false,"given":"Jiayi","family":"Guan","sequence":"first","affiliation":[{"name":"Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China"}]},{"given":"Shangding","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Informatics, Technical University of Munich, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3909-488X","authenticated-orcid":false,"given":"Zhijun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4778-137X","authenticated-orcid":false,"given":"Jing","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China"}]},{"given":"Yiqin","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Automation and Institute for Interdisciplinary Information Sciences, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7416-592X","authenticated-orcid":false,"given":"Guang","family":"CHen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Automotive Engineering, Tongji-Qomolo Autonomous Driving Commercial Vehicle Joint Lab, Tongji University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0637-9317","authenticated-orcid":false,"given":"Changjun","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Tongji University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.3034452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3198259"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16569"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3240323.3240374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20259"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2649564"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/robotics11040081"},{"issue":"11","key":"ref10","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1016\/j.robot.2012.05.019","article-title":"Real-world reinforcement learning for autonomous humanoid robot docking","volume":"60","author":"Navarro-Guerrero","year":"2012","journal-title":"Robot. Auton. Syst."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23232-9_21"},{"key":"ref12","first-page":"1","article-title":"GenDICE: Generalized offline estimation of stationary values","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref14","first-page":"11702","article-title":"Bridging offline reinforcement learning and imitation learning: A tale of pessimism","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Rashidinejad"},{"key":"ref15","first-page":"27395","article-title":"Policy finetuning: Bridging sample-efficient offline and online reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00718"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01131"},{"key":"ref18","first-page":"24753","article-title":"NeoRL: A near real-world benchmark for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Qin"},{"key":"ref19","first-page":"9072","article-title":"On the role of discount factor in offline reinforcement learning","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","volume":"162","author":"Hu"},{"key":"ref20","first-page":"1","article-title":"Offline reinforcement learning with value-based episodic memory","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ma"},{"key":"ref21","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref22","first-page":"2701","article-title":"Minimax-optimal off-policy evaluation with linear function approximation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref23","first-page":"1","article-title":"The importance of pessimism in fixed-dataset policy optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Buckman"},{"key":"ref24","first-page":"1","article-title":"Keep doing what worked: Behavior modelling priors for offline reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Siegel"},{"key":"ref25","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020","journal-title":"arXiv:2005.01643"},{"key":"ref26","first-page":"2001","article-title":"Generalized off-policy actor-critic","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Zhang"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20886"},{"key":"ref28","first-page":"1264","article-title":"Provably good batch off-policy reinforcement learning without great exploration","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Liu"},{"key":"ref29","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Fujimoto"},{"key":"ref30","first-page":"1042","article-title":"Information-theoretic considerations in batch reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref31","first-page":"7768","article-title":"Critic regularized regression","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Wang"},{"key":"ref32","first-page":"5084","article-title":"Is pessimism provably efficient for offline RL?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jin"},{"key":"ref33","first-page":"6683","article-title":"Bellman-consistent pessimism for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref34","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Yu"},{"key":"ref35","first-page":"28954","article-title":"Combo: Conservative offline model-based policy optimization","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yu"},{"key":"ref36","first-page":"10299","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref37","first-page":"1","article-title":"PLAS: Latent action space for offline reinforcement learning","volume-title":"Proc. Int. Conf. Robot Learn.","author":"Zhou"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/492"},{"key":"ref39","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019","journal-title":"arXiv:1911.11361"},{"key":"ref40","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kumar"},{"key":"ref41","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified Q-ensemble","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"An"},{"volume-title":"Reinforcement Learning: An Introduction","year":"2018","author":"Sutton","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref44","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal"},{"key":"ref45","first-page":"1","article-title":"Near-optimal offline reinforcement learning with linear representation: Leveraging variance information with pessimism","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yin"},{"key":"ref46","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747886"},{"key":"ref48","first-page":"21810","article-title":"MOReL: Model-based offline reinforcement learning","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kidambi"},{"key":"ref49","first-page":"3024","article-title":"Improving multi-step prediction of learned time series models","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"29","author":"Venkatraman"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2017.00010"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07949-0"},{"key":"ref52","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"arXiv:2004.07219"},{"key":"ref53","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chen"},{"key":"ref54","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kostrikov"},{"key":"ref55","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Janner"},{"key":"ref56","first-page":"4933","article-title":"Offline RL without off-policy evaluation","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Brandfonbrener"},{"key":"ref57","first-page":"11784","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Kumar"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7274989\/10491577\/10158415.pdf?arnumber=10158415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,10]],"date-time":"2024-04-10T18:27:10Z","timestamp":1712773630000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10158415\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":57,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2023.3287987","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}