{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T18:10:57Z","timestamp":1773166257854,"version":"3.50.1"},"reference-count":19,"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-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency\u2019s Mirai Program","doi-asserted-by":"publisher","award":["JPMJMI20B8"],"award-info":[{"award-number":["JPMJMI20B8"]}],"id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3106662","type":"journal-article","created":{"date-parts":[[2021,8,23]],"date-time":"2021-08-23T20:39:26Z","timestamp":1629751166000},"page":"117981-117992","source":"Crossref","is-referenced-by-count":20,"title":["An Empirical Investigation of Early Stopping Optimizations in Proximal Policy Optimization"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0572-692X","authenticated-orcid":false,"given":"Rousslan Fernand Julien","family":"Dossa","sequence":"first","affiliation":[{"name":"Graduate School of System Informatics, Kobe University, Hyogo, Japan"}]},{"given":"Shengyi","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computing & Informatics, Drexel University, Philadelphia, PA, USA"}]},{"given":"Santiago","family":"Ontanon","sequence":"additional","affiliation":[{"name":"College of Computing & Informatics, Drexel University, Philadelphia, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0642-4800","authenticated-orcid":false,"given":"Takashi","family":"Matsubara","sequence":"additional","affiliation":[{"name":"Graduate School of Engineering Science, Osaka University, Osaka, Japan"}]}],"member":"263","reference":[{"key":"ref10","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"arXiv 1506 02438 [cs]"},{"key":"ref11","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref12","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref13","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 35th Int Conf Mach Learn"},{"key":"ref14","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref15","article-title":"Go-explore: A new approach for hard-exploration problems","author":"ecoffet","year":"2019","journal-title":"arXiv 1901 10995"},{"key":"ref16","author":"weng","year":"2018","journal-title":"Policy-gradient algorithms for POMDPs"},{"key":"ref17","first-page":"267","article-title":"Approximately optimal approximate reinforcement learning","author":"kakade","year":"2002","journal-title":"Proc 19th Int Conf Mach Learn"},{"key":"ref18","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"arXiv 1602 01783"},{"key":"ref19","article-title":"Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation","author":"wu","year":"2017","journal-title":"arXiv 1708 05144"},{"key":"ref4","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref3","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref6","author":"achiam","year":"2018","journal-title":"Spinning up in deep reinforcement learning"},{"key":"ref5","first-page":"1","article-title":"Implementation matters in deep RL: A case study on PPO and TRPO","author":"engstrom","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref8","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref2","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref9","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09520424.pdf?arnumber=9520424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T20:26:02Z","timestamp":1662668762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9520424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3106662","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}