{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T05:40:22Z","timestamp":1730266822288,"version":"3.28.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10651193","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Remember the Past for Better Future: Memory-Augmented Offline RL"],"prefix":"10.1109","author":[{"given":"Yue","family":"Zhang","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,EEIS Department"}]},{"given":"Yaodong","family":"Yang","sequence":"additional","affiliation":[{"name":"Peking University,Institute for AI"}]},{"given":"Zhenbo","family":"Lu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence,Hefei Comprehensive National Science Center"}]},{"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,EEIS Department"}]},{"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,EEIS Department"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2016.04.036"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/1534582302001003001"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1058"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.nlm.2014.02.002","article-title":"Hippocampal-cortical interaction in decision making","volume":"117","author":"Jai","year":"2015","journal-title":"Neurobiology of learning and memory"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_15"},{"key":"ref6","first-page":"3929","article-title":"Retrieval augmented language model pre-training","volume-title":"International Conference on Machine Learning","author":"Guu"},{"key":"ref7","first-page":"9459","article-title":"Retrieval- augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Playing atari with deep reinforcement learning","year":"2013","author":"Mnih","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191777"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref14"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref15"},{"article-title":"Generalizable episodic memory for deep reinforcement learning","year":"2021","author":"Hu","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/365"},{"article-title":"The alberta plan for ai research","year":"2022","author":"Sutton","key":"ref18"},{"key":"ref19","article-title":"Fast deep reinforcement learning using online adjustments from the past","volume":"31","author":"Hansen","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref20","first-page":"20 092","article-title":"Large-scale retrieval for reinforcement learning","volume":"35","author":"Humphreys","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/h0080017"},{"article-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref22"},{"key":"ref23","first-page":"14129","article-title":"Mopo: Model-based offline policy optimization","volume":"33","author":"Yu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref24","first-page":"28 954","article-title":"Combo: Conservative offline model-based policy optimization","volume":"34","author":"Yu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"article-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref26"},{"key":"ref27","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume":"33","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref29","first-page":"21 810","article-title":"Morel: Model-based offline reinforcement learning","volume":"33","author":"Kidambi","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","year":"2022","author":"Bai","key":"ref30"},{"article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"Deep RL Workshop NeurIPS","author":"Kostrikov","key":"ref31"},{"article-title":"Mildly conservative q-learning for offline reinforcement learning","year":"2022","author":"Lyu","key":"ref32"},{"key":"ref33","first-page":"449","article-title":"Model-based offline reinforcement learning with pessimism-modulated dynamics belief","volume":"35","author":"Guo","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref34","article-title":"Rambo-rl: Robust adversarial model-based offline reinforcement learning","author":"Rigter","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","first-page":"2827","article-title":"Neural episodic control","volume-title":"International Conference on Machine Learning","author":"Pritzel"},{"article-title":"Model-free episodic control","year":"2016","author":"Blundell","key":"ref36"},{"key":"ref37","first-page":"7740","article-title":"Retrieval- augmented reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Goyal"},{"article-title":"Episodic reinforcement learning with associative memory","volume-title":"International Conference on Learning Representations","author":"Zhu","key":"ref38"},{"article-title":"Deepaveragers: Offline reinforcement learning by solving derived non-parametric mdps","year":"2020","author":"Shrestha","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/2291177"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Offlinerl-kit: An elegant pytorch offline reinforcement learning library","year":"2023","author":"Sun","key":"ref43"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref45","article-title":"When to trust your model: Model-based policy optimization","volume":"32","author":"Janner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2024,6,30]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10651193.pdf?arnumber=10651193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T04:37:01Z","timestamp":1725943021000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10651193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10651193","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}