{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T05:28:18Z","timestamp":1783402098715,"version":"3.54.6"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T00:00:00Z","timestamp":1698796800000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2023,11]]},"DOI":"10.1109\/tnnls.2022.3155483","type":"journal-article","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T20:56:27Z","timestamp":1647291387000},"page":"9054-9063","source":"Crossref","is-referenced-by-count":12,"title":["Robust Actor-Critic With Relative Entropy Regulating Actor"],"prefix":"10.1109","volume":"34","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":"ref13","article-title":"Authentic boundary proximal policy optimization","author":"cheng","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.011"},{"key":"ref15","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref14","article-title":"An off-policy trust region policy optimization method with monotonic improvement guarantee for deep reinforcement learning","author":"meng","year":"2021","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref31","article-title":"Soft actor-critic algorithms and applications","author":"haarnoja","year":"2018","journal-title":"arXiv 1812 05905"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3006850"},{"key":"ref33","first-page":"1352","article-title":"Reinforcement learning with deep energy-based policies","author":"haarnoja","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3056444"},{"key":"ref32","article-title":"Inference-based posteriori parameter distribution optimization","author":"wang","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927227"},{"key":"ref1","first-page":"2469","article-title":"Deep reinforcement learning for sequence-to-sequence models","volume":"31","author":"keneshloo","year":"2020","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"ref17","article-title":"Trust-PCL: An off-policy trust region method for continuous control","author":"nachum","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent"},{"key":"ref16","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref19","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume":"32","author":"silver","year":"2014","journal-title":"Proc ICML"},{"key":"ref18","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent"},{"key":"ref24","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","first-page":"573","article-title":"Online relative entropy policy search using reproducing kernel Hilbert space embeddings","author":"chen","year":"2016","journal-title":"Proc 19th Int Conf Artif Intell Statist"},{"key":"ref26","article-title":"Off-policy maximum entropy reinforcement learning: Soft actor-critic with advantage weighted mixture policy(SAC-AWMP)","author":"hou","year":"2020","journal-title":"arXiv 2002 02829"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/475"},{"key":"ref20","first-page":"1582","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref22","article-title":"Improving actor-critic reinforcement learning via Hamiltonian Monte Carlo method","author":"xu","year":"2021","journal-title":"arXiv 2103 12020"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2959129"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v24i1.7727"},{"key":"ref27","article-title":"Hierarchical reinforcement learning via advantage-weighted information maximization","author":"osa","year":"2019","journal-title":"Proc 7th Int Conf Learn Represent"},{"key":"ref29","article-title":"V-MPO: On-policy maximum a posteriori policy optimization for discrete and continuous control","author":"song","year":"2020","journal-title":"Proc 8th Int Conf Learn Represent"},{"key":"ref8","article-title":"Integrated double estimator architecture for reinforcement learning","author":"lv","year":"2021","journal-title":"IEEE Trans Cybern"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2979493"},{"key":"ref4","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2821369"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2898389"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10299535\/09733407.pdf?arnumber=9733407","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:27:14Z","timestamp":1700508434000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9733407\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11]]},"references-count":33,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3155483","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11]]}}}