{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T15:05:54Z","timestamp":1788879954456,"version":"build-2803163510"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["WDZC20200818121348001"],"award-info":[{"award-number":["WDZC20200818121348001"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010877","name":"Shenzhen Science and Technology Innovation Commission","doi-asserted-by":"publisher","award":["JCYJ20210324135011030"],"award-info":[{"award-number":["JCYJ20210324135011030"]}],"id":[{"id":"10.13039\/501100010877","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Innovation Committee of Shenzhen-Platform and Carrier"},{"name":"High-End Foreign Expert Talent Introduction Plan","award":["G2021032022L"],"award-info":[{"award-number":["G2021032022L"]}]},{"name":"Guangdong Pearl River Plan","award":["2019QN01X890"],"award-info":[{"award-number":["2019QN01X890"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71971127"],"award-info":[{"award-number":["71971127"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tg.2022.3224088","type":"journal-article","created":{"date-parts":[[2022,11,24]],"date-time":"2022-11-24T15:33:38Z","timestamp":1669304018000},"page":"102-112","source":"Crossref","is-referenced-by-count":4,"title":["Curriculum Goal-Conditioned Imitation for Offline Reinforcement Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4131-0625","authenticated-orcid":false,"given":"Xiaoyun","family":"Feng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Jiang","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5720-1215","authenticated-orcid":false,"given":"Xudong","family":"Yu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoran","family":"Xu","sequence":"additional","affiliation":[{"name":"JD Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3683-0554","authenticated-orcid":false,"given":"Xianyuan","family":"Zhan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7202-1922","authenticated-orcid":false,"given":"Wai Kin","family":"Chan","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"317","article-title":"Neural fitted Q iteration-first experiences with a data efficient neural reinforcement learning method","volume-title":"Proc. Eur. Conf. Mach. Learn.","author":"Martin","year":"2005"},{"key":"ref2","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"Natasha","year":"2019"},{"key":"ref3","article-title":"COG: Connecting new skills to past experience with offline reinforcement learning","author":"Singh","year":"2020"},{"key":"ref4","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto","year":"2019"},{"key":"ref5","first-page":"11761","article-title":"Stabilizing off-policy Q-learning via bootstrapping error reduction","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2019"},{"key":"ref6","article-title":"Behavior regularized offline reinforcement learning","author":"Wu","year":"2019"},{"key":"ref7","first-page":"1179","article-title":"Conservative Q-learning for offline reinforcement learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Kumar","year":"2020"},{"key":"ref8","first-page":"305","article-title":"ALVINN: An autonomous land vehicle in a neural network","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Pomerleau","year":"1989"},{"key":"ref9","article-title":"D4RL: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"},{"key":"ref10","first-page":"6266","article-title":"Curriculum offline imitating learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Liu","year":"2021"},{"key":"ref11","first-page":"11501","article-title":"Conservative data sharing for multi-task offline reinforcement learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref12","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2021"},{"key":"ref13","article-title":"RVS: What is essential for offline RL via supervised learning?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Emmons","year":"2022"},{"key":"ref14","article-title":"Reward-conditioned policies","author":"Kumar","year":"2019"},{"key":"ref15","article-title":"Offline reinforcement learning with soft behavior regularization","author":"Xu","year":"2021"},{"key":"ref16","first-page":"14129","article-title":"MOPO: Model-based offline policy optimization","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Yu","year":"2020"},{"key":"ref17","first-page":"21810","article-title":"Morel: Model-based offline reinforcement learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Kidambi","year":"2020"},{"key":"ref18","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Agarwal","year":"2020"},{"key":"ref19","article-title":"Offline reinforcement learning with implicit Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kostrikov","year":"2022"},{"key":"ref20","article-title":"Training agents using upside-down reinforcement learning","author":"Srivastava","year":"2019"},{"key":"ref21","article-title":"Reinforcement learning upside down: Dont predict rewardsjust map them to actions","author":"Schmidhuber","year":"2019"},{"key":"ref22","first-page":"15298","article-title":"Goal-conditioned imitation learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Ding","year":"2019"},{"key":"ref23","article-title":"Learning to reach goals via iterated supervised learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ghosh","year":"2021"},{"key":"ref24","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Proc. Conf. Robot Learn.","author":"Lynch","year":"2020"},{"key":"ref25","first-page":"3878","article-title":"Self-imitation learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oh","year":"2018"},{"key":"ref26","first-page":"1025","article-title":"Relay policy learning: Solving long-horizon tasks via imitation and reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Gupta","year":"2019"},{"key":"ref27","first-page":"1113","article-title":"Learning latent plans from play","volume-title":"Proc. Conf. Robot Learn.","author":"Lynch","year":"2019"},{"key":"ref28","first-page":"10265","article-title":"Policy continuation with hindsight inverse dynamics","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Sun","year":"2019"},{"key":"ref29","first-page":"7207","article-title":"Goal-aware prediction: Learning to model what matters","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nair","year":"2020"},{"key":"ref30","article-title":"Visual foresight: Model-based deep reinforcement learning for vision-based robotic control","author":"Ebert","year":"2018"},{"key":"ref31","first-page":"1094","article-title":"Learning to achieve goals","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Kaelbling","year":"1993"},{"key":"ref32","first-page":"1312","article-title":"Universal value function approximators","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Schaul","year":"2015"},{"key":"ref33","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref34","first-page":"5048","article-title":"Hindsight experience replay","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Andrychowicz","year":"2017"},{"key":"ref35","article-title":"Temporal difference models: Model-free deep RL for model-based control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Pong","year":"2018"},{"key":"ref36","article-title":"Semi-parametric topological memory for navigation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Savinov","year":"2018"},{"key":"ref37","first-page":"15220","article-title":"Search on the replay buffer: Bridging planning and reinforcement learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Eysenbach","year":"2019"},{"key":"ref38","first-page":"14814","article-title":"Planning with goal-conditioned policies","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Nasiriany","year":"2019"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01289"},{"key":"ref40","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhao","year":"2019"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3054912"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5373486"},{"key":"ref43","first-page":"12602","article-title":"Curriculum-guided hindsight experience replay","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Fang","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1603_1"},{"key":"ref45","article-title":"Accelerating online reinforcement learning with offline datasets","author":"Nair","year":"2020"},{"key":"ref46","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","year":"2018"},{"key":"ref47","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proc. Int. Adv. Conf. Neural Inf. Process. Syst.","author":"Fujimoto","year":"2021"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10474491\/09962804.pdf?arnumber=9962804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T07:00:05Z","timestamp":1725606005000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9962804\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":47,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3224088","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"value":"2475-1502","type":"print"},{"value":"2475-1510","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}