{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:40:07Z","timestamp":1735198807551,"version":"3.32.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802094","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"12625-12631","source":"Crossref","is-referenced-by-count":0,"title":["Environment Transformer and Policy Optimization for Model-Based Offline Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Pengqin","family":"Wang","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology,Division of Emerging Interdisciplinary Areas,Hong Kong SAR, China"}]},{"given":"Meixin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou),Systems Hub"}]},{"given":"Shaojie","family":"Shen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981126"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3190100"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811963"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2020.2993215"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3236945"},{"key":"ref9","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"International conference on machine learning","author":"Haarnoja"},{"key":"ref10","first-page":"2052","article-title":"Off-Policy Deep Reinforcement Learning without Exploration","volume-title":"International Conference on Machine Learning","author":"Fujimoto"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-27645-3_2"},{"key":"ref12","article-title":"When to Trust Your Model: Model-Based Policy Optimization","author":"Janner","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","volume":"31","author":"Chua","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","first-page":"29420","article-title":"Offline reinforcement learning with reverse model-based imagination","volume":"34","author":"Wang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"21810","article-title":"Morel: Model-based offline reinforcement learning","volume":"33","author":"Kidambi","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"MOPO: Model-based Offline Policy Optimization","year":"2020","author":"Yu","key":"ref16"},{"key":"ref17","first-page":"28954","article-title":"COMBO: Conservative Offline Model-Based Policy Optimization","volume":"34","author":"Yu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.2307\/jj.20206644.79"},{"article-title":"Conservative Q-Learning for Offline Reinforcement Learning","year":"2020","author":"Kumar","key":"ref19"},{"key":"ref20","first-page":"7768","article-title":"Critic Regularized Regression","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","year":"2020","author":"Nair","key":"ref21"},{"article-title":"Behavior regularized offline reinforcement learning","year":"2019","author":"Wu","key":"ref22"},{"article-title":"PLAS: Latent Action Space for Offline Reinforcement Learning","year":"2020","author":"Zhou","key":"ref23"},{"article-title":"Offline Reinforcement Learning with Implicit Q-Learning","year":"2021","author":"Kostrikov","key":"ref24"},{"article-title":"Offline Reinforcement Learning with Soft Behavior Regularization","year":"2021","author":"Xu","key":"ref25"},{"key":"ref26","first-page":"20132","article-title":"A Minimalist Approach to Offline Reinforcement Learning","volume":"34","author":"Fujimoto","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"key":"ref28","first-page":"465","article-title":"PILCO: A Model-Based and Data-Efficient Approach to Policy Search","volume-title":"Proceedings of the 28th International Conference on Machine Learning","author":"Deisenroth"},{"key":"ref29","first-page":"1","article-title":"Guided Policy Search","volume-title":"Proceedings of the 30th International Conference on Machine Learning","volume":"28","author":"Levine"},{"key":"ref30","article-title":"Sequence to Sequence Learning with Neural Networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref32"},{"article-title":"Decision Transformer: Reinforcement Learning via Sequence Modeling","year":"2021","author":"Chen","key":"ref33"},{"key":"ref34","first-page":"1273","article-title":"Offline Reinforcement Learning as One Big Sequence Modeling Problem","volume":"34","author":"Janner","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"D4rl: Datasets for deep data-driven reinforcement learning","year":"2020","author":"Fu","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04921-7_39"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9481.003.0015"},{"article-title":"High-dimensional continuous control using generalized advantage estimation","year":"2015","author":"Schulman","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3605573.3605613"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802094.pdf?arnumber=10802094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:59:34Z","timestamp":1735196374000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802094\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802094","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}