{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,18]],"date-time":"2025-01-18T05:07:21Z","timestamp":1737176841418,"version":"3.33.0"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,15]],"date-time":"2024-12-15T00:00:00Z","timestamp":1734220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,12,15]]},"DOI":"10.1109\/bigdata62323.2024.10825395","type":"proceedings-article","created":{"date-parts":[[2025,1,16]],"date-time":"2025-01-16T18:31:23Z","timestamp":1737052283000},"page":"1161-1166","source":"Crossref","is-referenced-by-count":0,"title":["Quality-Aware Experience Exploitation in Model-Based Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Guang","family":"Yang","sequence":"first","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahe","family":"Li","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziye","family":"Geng","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changqing","family":"Luo","sequence":"additional","affiliation":[{"name":"Virginia Commonwealth University,Dept. of Computer Science,Richmond,VA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1861","article-title":"Soft actor-critic: Offpolicy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Haarnoja"},{"key":"ref2","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Fujimoto"},{"key":"ref3","article-title":"Double q-learning","volume-title":"Advances in Neural Information Processing Systems","volume":"23","author":"Hasselt","year":"2010"},{"key":"ref4","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Buckman"},{"article-title":"Model-ensemble trust-region policy optimization","volume-title":"International Conference on Learning Representations","author":"Kurutach","key":"ref5"},{"article-title":"When to trust your model: model-based policy optimization","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"Janner","key":"ref6"},{"key":"ref7","first-page":"5618","article-title":"Bidirectional model-based policy optimization","volume-title":"Proceedings of the 37th International Conference on Machine Learning","volume":"119","author":"Lai"},{"article-title":"Trust the model when it is confident: masked model-based actor-critic","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Pan","key":"ref8"},{"article-title":"Model-based policy optimization with unsupervised model adaptation","volume-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems","author":"Shen","key":"ref9"},{"volume-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-022-3696-5"},{"article-title":"Model-based reinforcement learning: A survey","year":"2022","author":"Moerland","key":"ref12"},{"key":"ref13","first-page":"264","article-title":"Lipschitz continuity in model-based reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning","volume":"80","author":"Asadi"},{"key":"ref14","article-title":"Iterative value-aware model learning","volume":"31","author":"Farahmand","year":"2018","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref15","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume-title":"Proceedings of the 32nd International Conference on Neural Information Processing Systems","author":"Chua"},{"key":"ref16","article-title":"Recurrent world models facilitate policy evolution","author":"Ha","year":"2018","journal-title":"Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt4cgngj.10"},{"article-title":"Accelerating representation learning with view-consistent dynamics in data-efficient reinforcement learning","year":"2022","author":"Huang","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17276"},{"article-title":"Mastering atari with discrete world models","volume-title":"International Conference on Learning Representations","author":"Hafner","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/122344.122377"},{"article-title":"Algorithmic framework for model-based deep reinforcement learning with theoretical guarantees","volume-title":"International Conference on Learning Representations","author":"Luo","key":"ref23"},{"key":"ref24","article-title":"Actor-critic algorithms","volume-title":"Advances in Neural Information Processing Systems","volume":"12","author":"Konda","year":"1999"}],"event":{"name":"2024 IEEE International Conference on Big Data (BigData)","start":{"date-parts":[[2024,12,15]]},"location":"Washington, DC, USA","end":{"date-parts":[[2024,12,18]]}},"container-title":["2024 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10824975\/10824942\/10825395.pdf?arnumber=10825395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T08:18:32Z","timestamp":1737101912000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10825395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,15]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/bigdata62323.2024.10825395","relation":{},"subject":[],"published":{"date-parts":[[2024,12,15]]}}}