{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T10:51:36Z","timestamp":1770288696375,"version":"3.49.0"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,1]],"date-time":"2022-05-01T00:00:00Z","timestamp":1651363200000},"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":["61772532"],"award-info":[{"award-number":["61772532"]}],"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":["U1813203"],"award-info":[{"award-number":["U1813203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFA0706200"],"award-info":[{"award-number":["2019YFA0706200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1703600"],"award-info":[{"award-number":["2019YFB1703600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1109\/tcyb.2020.3023127","type":"journal-article","created":{"date-parts":[[2020,10,7]],"date-time":"2020-10-07T19:37:28Z","timestamp":1602099448000},"page":"3006-3017","source":"Crossref","is-referenced-by-count":9,"title":["Inference-Based Posteriori Parameter Distribution Optimization"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China"}]},{"given":"Tianyi","family":"Li","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Engineering Research Center of Intelligent Control for Underground Space, Ministry of Education, China University of Mining and Technology, Xuzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"Faculty of Science and Technology, University of Macau, Macau, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref2","first-page":"5732","article-title":"Problem dependent reinforcement learning bounds which can identify bandit structure in MDPs","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Zanette"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2019.2892151"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2983860"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2019.2937768"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2912212"},{"issue":"1","key":"ref13","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2585520"},{"key":"ref15","article-title":"Learning to navigate in complex environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mirowski"},{"key":"ref16","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zoph"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00853"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00081"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280949"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2869623"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2921057"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2831447"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CCAA.2017.8229841"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2868715"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761841"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref28","first-page":"2754","article-title":"Exploration: A study of count-based exploration for deep reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Tang"},{"key":"ref29","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref30","article-title":"Sample efficient actor-critic with experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2761878"},{"key":"ref32","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref33","article-title":"Parameter space noise for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Plappert"},{"key":"ref34","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fortunato"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/bf00992696"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2019.2931946"},{"key":"ref37","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref38","first-page":"1613","article-title":"Weight uncertainty in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell"},{"key":"ref39","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref40","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref41","first-page":"2976","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":"ref42","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Munos"},{"key":"ref43","first-page":"2587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Scott"},{"key":"ref44","volume-title":"OpenAI gym","author":"Brockman","year":"2016"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref46","first-page":"2850","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref47","volume-title":"High-dimensional continuous control using generalized advantage estimation","author":"Schulman","year":"2015"},{"key":"ref48","volume-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9778253\/09216634.pdf?arnumber=9216634","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,10]],"date-time":"2024-01-10T00:24:26Z","timestamp":1704846266000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9216634\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5]]},"references-count":48,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2020.3023127","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5]]}}}