{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:41Z","timestamp":1740102761179,"version":"3.37.3"},"reference-count":19,"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447908","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"5010-5014","source":"Crossref","is-referenced-by-count":0,"title":["Offline Reinforcement Learning with Policy Guidance and Uncertainty Estimation"],"prefix":"10.1109","author":[{"given":"Lan","family":"Wu","sequence":"first","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}]},{"given":"Quan","family":"Liu","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}]},{"given":"Zhigang","family":"Huang","sequence":"additional","affiliation":[{"name":"Soochow University,School of Computer Science and Technology,Soochow,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3236579"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21424"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2022.126485"},{"key":"ref5","first-page":"1711","article-title":"Mildly conservative q-learning for offline reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Lyu"},{"key":"ref6","first-page":"20132","article-title":"A minimalist approach to offline reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Fujimoto"},{"key":"ref7","first-page":"31278","article-title":"Supported policy optimization for offline reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Wu"},{"key":"ref8","first-page":"1179","article-title":"Conservative q-learning for offline reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Kumar"},{"article-title":"Rvs: What is essential for offline RL via supervised learning?","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Emmons","key":"ref9"},{"key":"ref10","first-page":"14639","article-title":"Versatile offline imitation from observations and examples via regularized state-occupancy matching","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Jason Ma"},{"key":"ref11","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":"ref12","first-page":"1719","article-title":"PLAS: latent action space for offline reinforcement learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"Zhou"},{"key":"ref13","first-page":"7902","article-title":"Learning pseudometric-based action representations for offline reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Gu"},{"key":"ref14","first-page":"7436","article-title":"Uncertainty-based offline reinforcement learning with diversified q-ensemble","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"An"},{"article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Bai","key":"ref15"},{"article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hafner","key":"ref16"},{"key":"ref17","first-page":"11319","article-title":"Uncertainty weighted actor-critic for offline reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Wu"},{"article-title":"D4RL: datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref18"},{"key":"ref19","first-page":"11761","article-title":"Stabilizing off-policy q-learning via bootstrapping error reduction","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Kumar"}],"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\/10447908.pdf?arnumber=10447908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T06:23:39Z","timestamp":1722579819000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447908\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447908","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}