{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T19:39:40Z","timestamp":1767987580562,"version":"3.49.0"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10448500","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"7520-7524","source":"Crossref","is-referenced-by-count":2,"title":["A New Pre-Training Paradigm for Offline Multi-Agent Reinforcement Learning with Suboptimal Data"],"prefix":"10.1109","author":[{"given":"Linghui","family":"Meng","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dengpeng","family":"Xing","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019"},{"key":"ref2","article-title":"Fever basketball: A complex, flexible, and asynchronized sports game environment for multi-agent reinforcement learning","author":"Jia","year":"2020"},{"key":"ref3","article-title":"Agent-centric representations for multi-agent reinforcement learning","author":"Shang","year":"2021"},{"key":"ref4","article-title":"Smarts: Scalable multi-agent reinforcement learning training school for autonomous driving","author":"Zhou","year":"2020"},{"key":"ref5","article-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems","author":"Levine","year":"2020"},{"key":"ref6","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref7","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020"},{"key":"ref8","first-page":"11 784","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Kumar"},{"key":"ref9","article-title":"Believe what you see: Implicit constraint approach for offline multi-agent reinforcement learning","volume-title":"Advances in Neural Information Processing Systems","volume":"34","author":"Yang"},{"key":"ref10","article-title":"Decision transformer: Reinforcement learning via sequence modeling","author":"Chen","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1383-7"},{"key":"ref12","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"ref13","article-title":"Offline multi-agent reinforcement learning with knowledge distillation","volume-title":"Thirty-Sixth Conference on Neural Information Processing Systems","author":"Tseng"},{"key":"ref14","first-page":"6818","article-title":"Imitation learning from imperfect demonstration","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref15","article-title":"Variational inverse control with events: A general framework for data-driven reward definition","volume-title":"Advances in Neural Information Processing Systems","volume":"31","author":"Fu"},{"key":"ref16","article-title":"Learning from suboptimal demonstration via self-supervised reward regression","author":"Chen","year":"2020"},{"key":"ref17","article-title":"How to leverage unlabeled data in offline reinforcement learning","author":"Yu","year":"2022"},{"key":"ref18","first-page":"arXiv","article-title":"Representation learning with contrastive predictive coding","author":"Van den Oord","year":"2018"},{"key":"ref19","article-title":"The surprising effectiveness of mappo in cooperative, multi-agent games","author":"Yu","year":"2021"},{"key":"ref20","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"ICML","author":"Whiteson"},{"key":"ref21","first-page":"4767","article-title":"Multi-task reinforcement learning with soft modularization","volume-title":"Advances in Neural Information Processing Systems","volume":"33","author":"Yang"},{"key":"ref22","article-title":"D4rl: Datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10448500.pdf?arnumber=10448500","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,3]],"date-time":"2024-08-03T04:43:14Z","timestamp":1722660194000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10448500\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10448500","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}