{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T03:24:34Z","timestamp":1783481074046,"version":"3.55.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,12,1]],"date-time":"2023-12-01T00:00:00Z","timestamp":1701388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0107200"],"award-info":[{"award-number":["2020AAA0107200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61921006"],"award-info":[{"award-number":["61921006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,12]]},"DOI":"10.1109\/tpami.2023.3317131","type":"journal-article","created":{"date-parts":[[2023,9,19]],"date-time":"2023-09-19T17:59:26Z","timestamp":1695146366000},"page":"15260-15274","source":"Crossref","is-referenced-by-count":6,"title":["Offline Model-Based Adaptable Policy Learning for Decision-Making in Out-of-Support Regions"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4911-3148","authenticated-orcid":false,"given":"Xiong-Hui","family":"Chen","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1062-8726","authenticated-orcid":false,"given":"Fan-Ming","family":"Luo","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1732-9545","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6650-2343","authenticated-orcid":false,"given":"Qingyang","family":"Li","sequence":"additional","affiliation":[{"name":"DiDi Labs, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-4816","authenticated-orcid":false,"given":"Zhiwei","family":"Qin","sequence":"additional","affiliation":[{"name":"DiDi Labs, Mountain View, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9331-4062","authenticated-orcid":false,"given":"Wenjie","family":"Shang","sequence":"additional","affiliation":[{"name":"DiDi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8662-5818","authenticated-orcid":false,"given":"Jieping","family":"Ye","sequence":"additional","affiliation":[{"name":"DiDi Chuxing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Off-policy deep reinforcement learning without exploration","author":"fujimoto","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref12","article-title":"Keep doing what worked: Behavior modelling priors for offline reinforcement learning","author":"siegel","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref15","article-title":"MOPO: Model-based offline policy optimization","author":"yu","year":"2020"},{"key":"ref14","first-page":"11761","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","author":"kumar","year":"2019","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref11","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"levine","year":"2020"},{"key":"ref10","first-page":"3632","article-title":"Off-policy evaluation for slate recommendation","author":"swaminathan","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref17","first-page":"1905","article-title":"Agnostic system identification for model-based reinforcement learning","author":"ross","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref16","first-page":"12498","article-title":"When to trust your model: Model-based policy optimization","author":"janner","year":"2019","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref18","article-title":"MOReL: Model-based offline reinforcement learning","author":"kidambi","year":"2020"},{"key":"ref46","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","author":"kumar","year":"2020","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref45","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"fu","year":"2020"},{"key":"ref48","article-title":"Varibad: A very good method for bayes-adaptive deep RL via meta-learning","author":"zintgraf","year":"2020","journal-title":"Proc 8th Int Conf Learn Representations"},{"key":"ref47","article-title":"Neorl: A near real-world benchmark for offline reinforcement learning","author":"qin","year":"2021"},{"key":"ref42","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref41","article-title":"Solving rubik's cube with a robot hand","author":"akkaya","year":"2019"},{"key":"ref44","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref8","first-page":"651","article-title":"Scalable deep reinforcement learning for vision-based robotic manipulation","author":"kalashnikov","year":"2018","journal-title":"Proc 2nd Annu Conf Robot Learn"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917710318"},{"key":"ref9","article-title":"Learning when-to-treat policies","author":"nie","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"ref3","article-title":"Deep reinforcement learning for online advertising in recommender systems","author":"zhao","year":"2019"},{"key":"ref6","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018"},{"key":"ref5","article-title":"Learning agile robotic locomotion skills by imitating animals","author":"peng","year":"2020"},{"key":"ref40","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","article-title":"Autoregressive dynamics models for offline policy evaluation and optimization","author":"zhang","year":"2021","journal-title":"Proc 9th Int Conf Learn Representations"},{"key":"ref34","article-title":"Context-aware dynamics model for generalization in model-based reinforcement learning","author":"lee","year":"2020"},{"key":"ref37","article-title":"Adversarial counterfactual environment model learning","author":"chen","year":"2022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330933"},{"key":"ref31","first-page":"5331","article-title":"Efficient off-policy meta-reinforcement learning via probabilistic context variables","author":"rakelly","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref33","article-title":"Environment probing interaction policies","author":"zhou","year":"2019","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.048"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00074"},{"key":"ref39","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref38","article-title":"Offline reinforcement learning with causal structured world models","author":"zhu","year":"2022"},{"key":"ref24","article-title":"Behavior regularized offline reinforcement learning","author":"wu","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref26","article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","author":"bai","year":"2022"},{"key":"ref25","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","author":"agarwal","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3159652.3159687"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i2.19104"},{"key":"ref21","first-page":"1806","article-title":"Personalized ad recommendation systems for life-time value optimization with guarantees","author":"theocharous","year":"2015","journal-title":"Proc 25th Int Joint Conf Artif Intell"},{"key":"ref28","article-title":"RL2: Fast reinforcement learning via slow reinforcement learning","author":"duan","year":"2016"},{"key":"ref27","article-title":"Viper: Provably efficient algorithm for offline RL with neural function approximation","author":"nguyen-tang","year":"2023","journal-title":"Proc 11th Int Conf Learn Representations"},{"key":"ref29","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"finn","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10308548\/10255284.pdf?arnumber=10255284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:09:48Z","timestamp":1736366988000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10255284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12]]},"references-count":49,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3317131","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12]]}}}