{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:52:52Z","timestamp":1740102772667,"version":"3.37.3"},"reference-count":20,"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\/icassp48485.2024.10446266","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"5255-5259","source":"Crossref","is-referenced-by-count":0,"title":["Offline Reinforcement Learning with Generative Adversarial Networks 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","first-page":"8302","article-title":"Vector quantized models for planning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Ozair"},{"key":"ref3","first-page":"24707","article-title":"Planning from pixels in environments with combinatorially hard search spaces","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Bagatella"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161096"},{"key":"ref5","first-page":"32974","article-title":"Vrl3: A data-driven framework for visual deep reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Wang"},{"key":"ref6","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":"ref7","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"},{"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"},{"key":"ref9","first-page":"5774","article-title":"Offline reinforcement learning with fisher divergence critic regularization","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Kostrikov"},{"key":"ref10","first-page":"104","article-title":"An optimistic perspective on offline reinforcement learning","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Agarwal"},{"article-title":"Pessimistic bootstrapping for uncertainty-driven offline reinforcement learning","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Bai","key":"ref11"},{"key":"ref12","first-page":"4085","article-title":"A policy-guided imitation approach for offline reinforcement learning","volume-title":"Proceedings of the Advances in Neural Information Processing Systems","author":"Xu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.03.108"},{"key":"ref14","first-page":"1719","article-title":"PLAS: latent action space for offline reinforcement learning","volume-title":"Proceedings of the Conference on Robot Learning","author":"Zhou"},{"article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Hafner","key":"ref15"},{"key":"ref16","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"},{"key":"ref17","first-page":"19967","article-title":"Pessimistic q-learning for offline reinforcement learning: Towards optimal sample complexity","volume-title":"International Conference on Machine Learning","author":"Shi"},{"journal-title":"D4RL: datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref18"},{"journal-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref19"},{"journal-title":"Advantage-weighted regression: Simple and scalable off-policy reinforcement learning","year":"2019","author":"Peng","key":"ref20"}],"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\/10446266.pdf?arnumber=10446266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T05:08:18Z","timestamp":1722575298000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10446266\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":20,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10446266","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}