{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T05:51:52Z","timestamp":1771566712707,"version":"3.50.1"},"reference-count":55,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","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":[{"name":"China National Research and Development Key Research Program","award":["2020YFB1711204"],"award-info":[{"award-number":["2020YFB1711204"]}]},{"name":"China National Research and Development Key Research Program","award":["2019YFB1705700"],"award-info":[{"award-number":["2019YFB1705700"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tcyb.2023.3254596","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T18:02:13Z","timestamp":1679508133000},"page":"3051-3064","source":"Crossref","is-referenced-by-count":8,"title":["Implicit Posteriori Parameter Distribution Optimization in Reinforcement Learning"],"prefix":"10.1109","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9423-6369","authenticated-orcid":false,"given":"Tianyi","family":"Li","sequence":"first","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3492-0211","authenticated-orcid":false,"given":"Genke","family":"Yang","sequence":"additional","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, China"}]},{"given":"Jian","family":"Chu","sequence":"additional","affiliation":[{"name":"Ningbo Artificial Intelligence Institute, Department of Automation, Shanghai Jiao Tong University, Shanghai, 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. Int. Conf. Mach. Learn.","author":"Zanette"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref4","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2983860"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-03157-9"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref11","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"},{"key":"ref12","volume-title":"Proximal Policy Optimization Algorithms","author":"Shulman","year":"2017"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2946122"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3085883"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1002\/asmb.2209"},{"key":"ref16","first-page":"1","article-title":"Learning to navigate in complex environments","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mirowski"},{"key":"ref17","first-page":"1","article-title":"Neural architecture search with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zoph"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref19","first-page":"2377","article-title":"Generalization and exploration via rarandomized value functions","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Osband"},{"key":"ref20","first-page":"9339","article-title":"Taylor expansion policy optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tang"},{"key":"ref21","first-page":"6","article-title":"Distributed distributional deterministic policy neuralgradients","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Barth-Maron"},{"key":"ref22","first-page":"2171","article-title":"Reinforcement learning with deep energy-based policies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref23","first-page":"2976","article-title":"Soft actor\u2013critic: Off-policy maximum deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref25","first-page":"1","article-title":"Exploration by random network distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Burda"},{"key":"ref26","first-page":"1","article-title":"Never give up: Learning directed exploration strategies","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Blundell"},{"key":"ref27","first-page":"387","article-title":"Deterministic policy gradient algorithms","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Silver"},{"key":"ref28","first-page":"5302","article-title":"Meta-reinforcement learning of structured exploration strategies","volume-title":"Poc. Adv. Neural Inf. Process. Syst.","author":"Mendonca"},{"key":"ref29","first-page":"1","article-title":"Parameter space noise for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Plappert"},{"key":"ref30","first-page":"6","article-title":"Noisy networks for exploration","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Fortunato"},{"key":"ref31","first-page":"449","article-title":"A distributional perspective on reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bellemare"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3053414"},{"key":"ref34","first-page":"1613","article-title":"Weight uncertainty in neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blundell"},{"key":"ref35","first-page":"7780","article-title":"Offline meta-reinforcement learning with advantage weighting","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mitchell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3023127"},{"key":"ref37","first-page":"4629","article-title":"What are Bayesian neural network posteriors really like","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Izmailov"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tcyb.2022.3170485"},{"key":"ref39","first-page":"1651","article-title":"Dropout as a Bayesian approximation: Representing model uncertainty in deep learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gal"},{"key":"ref40","volume-title":"Wasserstein Auto-Encoders","author":"Tolstikhin","year":"2017"},{"key":"ref41","first-page":"10957","article-title":"Training deep energy-based models with f-divergence minimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tetci.2022.3140380"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63833-7_38"},{"key":"ref44","first-page":"4033","article-title":"Deep exploration via bootstrapped DQN","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Osband"},{"key":"ref45","first-page":"1","article-title":"HyperDQN: A randomized exploration method for deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref46","first-page":"7985","article-title":"Implicit generative modeling for efficient exploration","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ratzlaff"},{"key":"ref47","first-page":"2378","article-title":"Stein variational gradient descent: A general purpose Bayesian inference algorithm","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref49","first-page":"9371","article-title":"HyperGAN: A generative model for diverse, performant neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ratzlaff"},{"key":"ref50","first-page":"1587","article-title":"Addressing function approximation error in actor\u2013critic methods","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref51","volume-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref53","volume-title":"Box2d: A Physics Engine for Games","author":"Catto","year":"2011"},{"key":"ref54","first-page":"1117","article-title":"VIME: Variational information maximizing exploration","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Houthooft"},{"key":"ref55","first-page":"9","article-title":"What matters for on-policy deep actor\u2013critic methods? A large-scale study","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Andrychowicz"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/10500879\/10078231.pdf?arnumber=10078231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T18:55:20Z","timestamp":1732906520000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10078231\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":55,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2023.3254596","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}