{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T11:36:22Z","timestamp":1785584182021,"version":"3.56.0"},"reference-count":40,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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","award":["61976215"],"award-info":[{"award-number":["61976215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176259"],"award-info":[{"award-number":["62176259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2022095"],"award-info":[{"award-number":["BE2022095"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tnnls.2022.3202192","type":"journal-article","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T19:48:38Z","timestamp":1663012118000},"page":"4286-4298","source":"Crossref","is-referenced-by-count":8,"title":["Dual Parallel Policy Iteration With Coupled Policy Improvement"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5123-5043","authenticated-orcid":false,"given":"Longyang","family":"Huang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, and the School of Information and Control Engineering, China University of Mining and Technology, Xuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3104612"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2021.3051456"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3084198"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3047730"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2795041"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5533"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2900035"},{"key":"ref9","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11768-011-1005-3"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3437992.3439927"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3098985"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2907991"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tac.2021.3085510"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2020.3004493"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2021.3071727"},{"key":"ref17","first-page":"511","article-title":"Robust reinforcement learning using least squares policy iteration with provable performance guarantees","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badrinath"},{"key":"ref18","first-page":"3692","article-title":"POLITEX: Regret bounds for policy iteration using expert prediction","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Yadkori"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2959129"},{"key":"ref20","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"2","author":"Kakade"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6070"},{"key":"ref22","first-page":"523","article-title":"Adaptive approximate policy iteration","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hao"},{"issue":"97","key":"ref23","first-page":"1","article-title":"Safe policy iteration: A monotonically improving approximate policy iteration approach","volume":"22","author":"Metelli","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref24","article-title":"Relative entropy regularized policy iteration","author":"Abdolmaleki","year":"2018","journal-title":"arXiv:1812.02256"},{"key":"ref25","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref26","first-page":"840","article-title":"Information theoretic model predictive Q-learning","volume-title":"Proc. Learn. Dyn. Control","author":"Bhardwaj"},{"key":"ref27","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.05905"},{"key":"ref29","first-page":"5366","article-title":"Thinking fast and slow with deep learning and tree search","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Anthony"},{"key":"ref30","first-page":"1071","article-title":"Learning neural network policies with guided policy search under unknown dynamics","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Levine"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref32","first-page":"7059","article-title":"Dual policy iteration","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Sun"},{"key":"ref33","volume-title":"Information Theory and Statistics","author":"Kullback","year":"1997"},{"key":"ref34","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3096966"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927227"},{"key":"ref37","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref38","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956703"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00061"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10454107\/09887982.pdf?arnumber=9887982","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T06:42:29Z","timestamp":1709361749000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9887982\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":40,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3202192","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}