{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:35:03Z","timestamp":1763202903912,"version":"3.28.0"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610701","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"10793-10799","source":"Crossref","is-referenced-by-count":2,"title":["Weighting Online Decision Transformer with Episodic Memory for Offline-to-Online Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Xiao","family":"Ma","sequence":"first","affiliation":[{"name":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,PRC,210023"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wu-Jun","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University,National Key Laboratory for Novel Software Technology,Department of Computer Science and Technology,Nanjing,PRC,210023"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780195100273.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038"},{"key":"ref3","article-title":"Model-free episodic control","volume":"abs\/1606.04460","author":"Blundell","year":"2016","journal-title":"CoRR"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Decision transformer: Reinforcement learning via sequence modeling","author":"Chen","year":"2021","journal-title":"NeurIPS"},{"key":"ref6","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref8","article-title":"Rvs: What is essential for offline RL via supervised learning?","author":"Emmons","year":"2022","journal-title":"ICLR"},{"key":"ref9","article-title":"D4RL: datasets for deep data-driven reinforcement learning","volume":"abs\/2004.07219","author":"Fu","year":"2020","journal-title":"CoRR"},{"key":"ref10","article-title":"Generalized decision transformer for offline hindsight information matching","author":"Furuta","year":"2022","journal-title":"ICLR"},{"key":"ref11","article-title":"Generalizable episodic memory for deep reinforcement learning","author":"Hu","year":"2021","journal-title":"ICML"},{"key":"ref12","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2017","journal-title":"ICLR"},{"key":"ref13","article-title":"Offline reinforcement learning as one big sequence modeling problem","author":"Janner","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636301"},{"key":"ref15","article-title":"Contrastive decision transformers","author":"Konan","year":"2022","journal-title":"CoRL"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1533\/9780857099440"},{"key":"ref17","article-title":"Offline reinforcement learning with implicit q-learning","author":"Kostrikov","year":"2022","journal-title":"ICLR"},{"key":"ref18","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/365"},{"key":"ref20","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","volume":"abs\/2005.01643","author":"Levine","year":"2020","journal-title":"CoRR"},{"key":"ref21","article-title":"A survey on transformers in reinforcement learning","volume":"abs\/2301.03044","author":"Li","year":"2023","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/337"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-023-06365-2"},{"key":"ref24","article-title":"Offline reinforcement learning with value-based episodic memory","author":"Ma","year":"2022","journal-title":"ICLR"},{"key":"ref25","article-title":"Accelerating online reinforcement learning with offline datasets","volume":"abs\/2006.09359","author":"Nair","year":"2020","journal-title":"CoRR"},{"key":"ref26","article-title":"Neural episodic control","author":"Pritzel","year":"2017","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204708"},{"key":"ref28","article-title":"Perceiver-actor: A multi-task transformer for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"CoRL"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlm.2004.06.005"},{"key":"ref30","article-title":"Training agents using upside-down reinforcement learning","volume":"abs\/1912.02877","author":"Srivastava","year":"2019","journal-title":"CoRR"},{"key":"ref31","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Bootstrapped transformer for offline reinforcement learning","author":"Wang","year":"2022","journal-title":"NeurIPS"},{"key":"ref33","article-title":"Future-conditioned unsupervised pretraining for decision transformer","author":"Xie","year":"2023","journal-title":"ICML"},{"key":"ref34","article-title":"Q-learning decision transformer: Leveraging dynamic programming for conditional sequence modelling in offline RL","author":"Yamagata","year":"2023","journal-title":"ICML"},{"key":"ref35","article-title":"Dichotomy of control: Separating what you can control from what you cannot","author":"Yang","year":"2023","journal-title":"ICLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cog57401.2023.10333131"},{"key":"ref37","first-page":"3757","article-title":"Episodic multi-agent reinforcement learning with curiosity-driven exploration","author":"Zheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref38","article-title":"Online decision transformer","author":"Zheng","year":"2022","journal-title":"ICML"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2024,5,13]]},"location":"Yokohama, Japan","end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610701.pdf?arnumber=10610701","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:53:26Z","timestamp":1723269206000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610701\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610701","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}