{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:07:24Z","timestamp":1772039244676,"version":"3.50.1"},"reference-count":20,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFC3300703"],"award-info":[{"award-number":["2022YFC3300703"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Science Foundation of China","doi-asserted-by":"publisher","award":["62003015"],"award-info":[{"award-number":["62003015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Intell. Syst."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/mis.2024.3386204","type":"journal-article","created":{"date-parts":[[2024,4,8]],"date-time":"2024-04-08T21:20:10Z","timestamp":1712611210000},"page":"63-72","source":"Crossref","is-referenced-by-count":3,"title":["Model Predictive Control-Based Value Estimation for Efficient Reinforcement Learning"],"prefix":"10.1109","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5819-1230","authenticated-orcid":false,"given":"Qizhen","family":"Wu","sequence":"first","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4328-6339","authenticated-orcid":false,"given":"Kexin","family":"Liu","sequence":"additional","affiliation":[{"name":"Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1859-384X","authenticated-orcid":false,"given":"Lei","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/mis.2022.3184427"},{"key":"ref2","first-page":"10,835","article-title":"Scaling laws for reward model overoptimization","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","author":"Gao","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ast.2021.106925"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2019.2903098"},{"key":"ref7","article-title":"Image augmentation is all you need: Regularizing deep reinforcement learning from pixels","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Kostrikov","year":"2021"},{"key":"ref8","first-page":"12519","article-title":"When to trust your model: Model-based policy optimization","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Janner","year":"2019"},{"key":"ref9","first-page":"10,537","article-title":"Trust the model when it is confident: Masked model-based actor-critic","volume":"33","author":"Pan","year":"2020","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2019.2913768"},{"key":"ref11","first-page":"8234","article-title":"Sample-efficient reinforcement learning with stochastic ensemble value expansion","volume":"31","author":"Buckman","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref12","first-page":"8387","article-title":"Temporal difference learning for model predictive control","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Hansen","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tii.2022.3142323"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(89)90002-2"},{"key":"ref15","first-page":"4759","article-title":"Deep reinforcement learning in a handful of trials using probabilistic dynamics models","volume":"31","author":"Chua","year":"2018","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/b978-1-55860-141-3.50030-4"},{"key":"ref17","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1080\/00207721.2014.929191"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"}],"container-title":["IEEE Intelligent Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9670\/10570357\/10494864.pdf?arnumber=10494864","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T21:48:12Z","timestamp":1719352092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10494864\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":20,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/mis.2024.3386204","relation":{},"ISSN":["1541-1672","1941-1294"],"issn-type":[{"value":"1541-1672","type":"print"},{"value":"1941-1294","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}