{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T15:11:49Z","timestamp":1774969909241,"version":"3.50.1"},"reference-count":27,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61850410527"],"award-info":[{"award-number":["61850410527"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Young Oriental Scholars","award":["0830000081"],"award-info":[{"award-number":["0830000081"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3094566","type":"journal-article","created":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T19:49:23Z","timestamp":1625514563000},"page":"96056-96063","source":"Crossref","is-referenced-by-count":15,"title":["A Functional Clipping Approach for Policy Optimization Algorithms"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1950-202X","authenticated-orcid":false,"given":"Wangshu","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science, School of Information Science and Technology, Living Machines Laboratories, ShanghaiTech University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4062-5390","authenticated-orcid":false,"given":"Andre","family":"Rosendo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, School of Information Science and Technology, Living Machines Laboratories, ShanghaiTech University, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref10","first-page":"267","article-title":"An analysis of actor-critic algorithms using eligibility traces: Reinforcement learning with imperfect value functions","volume":"15","author":"kimura","year":"2000","journal-title":"J Jpn Soc Artif Intell"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref12","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"levine","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793864"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2008.02.003"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"1607","DOI":"10.1609\/aaai.v24i1.7727","article-title":"Relative entropy policy search","volume":"10","author":"peters","year":"2010","journal-title":"Proc AAAI"},{"key":"ref18","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2015","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref4","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"ref3","first-page":"565","article-title":"Model-free trajectory-based policy optimization with monotonic improvement","volume":"19","author":"akrour","year":"2018","journal-title":"J Mach Learn Res"},{"key":"ref6","first-page":"315","article-title":"Deep sparse rectifier neural networks","author":"glorot","year":"2011","journal-title":"Proc 14th Int Conf Artif Intell Statist"},{"key":"ref5","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref8","article-title":"A closer look at deep policy gradients","author":"ilyas","year":"2018","journal-title":"arXiv 1811 02553"},{"key":"ref7","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2017","journal-title":"arXiv 1709 06560"},{"key":"ref2","first-page":"2961","article-title":"Model-free trajectory optimization for reinforcement learning","author":"akrour","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2016.7860433"},{"key":"ref1","first-page":"3537","article-title":"Model-based relative entropy stochastic search","author":"abdolmaleki","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref22","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref21","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of go with deep neural networks and tree search","volume":"529","author":"silver","year":"2016","journal-title":"Nature"},{"key":"ref24","article-title":"Deep reinforcement learning with double Q-learning","author":"van hasselt","year":"2015","journal-title":"arXiv 1509 06461 [cs]"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref26","article-title":"Truly proximal policy optimization","author":"wang","year":"2019","journal-title":"arXiv 1903 07940"},{"key":"ref25","first-page":"626","article-title":"Trust region-guided proximal policy optimization","author":"wang","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09474478.pdf?arnumber=9474478","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T22:32:20Z","timestamp":1672698740000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9474478\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3094566","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}