{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:52:51Z","timestamp":1761396771235,"version":"3.37.3"},"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012246","name":"Priority Academic Program Development of Jiangsu Higher Education Institutions","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012246","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\/icassp48485.2024.10446781","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"5775-5779","source":"Crossref","is-referenced-by-count":1,"title":["Offline Reinforcement Learning Based on Next State Supervision"],"prefix":"10.1109","author":[{"given":"Jie","family":"Yan","sequence":"first","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"ref2","article-title":"Cross DQN: cross deep Q network for ads allocation in feed","author":"Liao","year":"2021","journal-title":"CoRR"},{"key":"ref3","article-title":"Way off-policy batch deep reinforcement learning of implicit human preferences in dialog","author":"Jaques","year":"2019","journal-title":"CoRR"},{"key":"ref4","first-page":"2052","article-title":"Off-policy deep reinforcement learning without exploration","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref5","first-page":"11761","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","author":"Kumar","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","article-title":"Conservative q-learning for offline reinforcement learning","author":"Kumar","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Offline reinforcement learning with implicit q-learning","volume-title":"International Conference on Learning Representations","author":"Kostrikov","key":"ref7"},{"key":"ref8","first-page":"4933","article-title":"Offline RL without off-policy evaluation","author":"Brandfonbrener","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","article-title":"Mildly conservative q-learning for offline reinforcement learning","author":"Lyu","year":"2022","journal-title":"Neural Information Processing Systems"},{"key":"ref10","article-title":"A policy-guided imitation approach for offline reinforcement learning","author":"Xu","year":"2022","journal-title":"Neural Information Processing Systems"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref11"},{"article-title":"Learning to reach goals via iterated supervised learning","volume-title":"International Conference on Learning Representations","author":"Ghosh","key":"ref12"},{"article-title":"Rethinking goal-conditioned supervised learning and its connection to offline RL","volume-title":"International Conference on Learning Representations","author":"Yang","key":"ref13"},{"article-title":"Gpt-critic: Offline reinforcement learning for end-to-end task-oriented dialogue systems","volume-title":"International Conference on Learning Representations","author":"Jang","key":"ref14"},{"key":"ref15","first-page":"15753","article-title":"Beyond reward: Offline preference-guided policy optimization","volume-title":"International Conference on Machine Learning","author":"Kang"},{"key":"ref16","first-page":"34556","article-title":"Jump-start reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Uchendu"},{"key":"ref17","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26345"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3242734"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1707.06347"},{"key":"ref21","article-title":"SCORE: spurious correlation reduction for offline reinforcement learning","author":"Deng","year":"2021","journal-title":"CoRR"},{"key":"ref22","article-title":"D4RL: datasets for deep data-driven reinforcement learning","author":"Fu","year":"2020","journal-title":"CoRR"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2024,4,14]]},"location":"Seoul, Korea, Republic of","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\/10446781.pdf?arnumber=10446781","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:26:12Z","timestamp":1722576372000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446781\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446781","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}