{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T18:17:45Z","timestamp":1776277065566,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Syst. Man Cybern, Syst."],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1109\/tsmc.2019.2931946","type":"journal-article","created":{"date-parts":[[2019,8,30]],"date-time":"2019-08-30T21:03:29Z","timestamp":1567199009000},"page":"3771-3780","source":"Crossref","is-referenced-by-count":11,"title":["Proximal Parameter Distribution Optimization"],"prefix":"10.1109","volume":"51","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5327-1088","authenticated-orcid":false,"given":"Xuesong","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianyi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2022-9999","authenticated-orcid":false,"given":"Yuhu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref38","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref33","article-title":"Reptile: A scalable metalearning algorithm","author":"nichol","year":"2018","journal-title":"arXiv 1803 02999"},{"key":"ref32","first-page":"1613","article-title":"Weight uncertainty in neural networks","author":"blundell","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","first-page":"1109","article-title":"VIME: Variational information maximizing exploration","author":"houthooft","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref30","article-title":"Surprise-based intrinsic motivation for deep reinforcement learning","author":"achiam","year":"2017","journal-title":"arXiv 1703 01732"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"ref36","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"1999","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2500020"},{"key":"ref34","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref10","first-page":"4033","article-title":"Deep exploration via bootstrapped DQN","author":"osband","year":"2016","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref40","first-page":"2850","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","first-page":"2939","article-title":"Dueling network architectures for deep reinforcement learning","author":"wang","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2806087"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299173"},{"key":"ref14","article-title":"Some improvements on deep convolutional neural network based image classification","author":"howard","year":"2013","journal-title":"ArXiv 1312 5402"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCIAIG.2012.2186810"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2093548.2093574"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.70"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref27","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017","journal-title":"arXiv 1706 10295"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2015.2478885"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2605159"},{"key":"ref29","first-page":"2754","article-title":"#Exploration: A study of count-based exploration for deep reinforcement learning","author":"tang","year":"2016","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2017.2697842"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref7","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2016.2645699"},{"key":"ref9","first-page":"2094","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2016","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913495721"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989384"},{"key":"ref21","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2016","journal-title":"arXiv 1611 03673"},{"key":"ref24","first-page":"2377","article-title":"Generalization and exploration via randomized value functions","author":"osband","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref41","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref26","article-title":"Parameter space noise for exploration","author":"plappert","year":"2017","journal-title":"arXiv 1706 01905"},{"key":"ref25","first-page":"387","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Systems, Man, and Cybernetics: Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221021\/9433721\/08820176.pdf?arnumber=8820176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:53:24Z","timestamp":1652194404000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8820176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":41,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsmc.2019.2931946","relation":{},"ISSN":["2168-2216","2168-2232"],"issn-type":[{"value":"2168-2216","type":"print"},{"value":"2168-2232","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6]]}}}