{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:52Z","timestamp":1740169252411,"version":"3.37.3"},"reference-count":28,"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\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3097357","type":"journal-article","created":{"date-parts":[[2021,7,26]],"date-time":"2021-07-26T22:28:11Z","timestamp":1627338491000},"page":"101424-101432","source":"Crossref","is-referenced-by-count":4,"title":["Trajectory Based Prioritized Double Experience Buffer for Sample-Efficient Policy Optimization"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5948-4634","authenticated-orcid":false,"given":"Shengxiang","family":"Li","sequence":"first","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ou","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangyi","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Ding","sequence":"additional","affiliation":[{"name":"Key Laboratory of Experimental Physics and Computational Mathematics, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yijie","family":"Bai","sequence":"additional","affiliation":[{"name":"College of Information System and Engineering, PLA Strategy Support Force Information Engineering University, Zhengzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref11","first-page":"1054","article-title":"Safe and efficient off-policy reinforcement learning","author":"munos","year":"2016","journal-title":"Proc Annu Conf Neural Inf Process Syst"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref13","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref14","first-page":"457","article-title":"Off-policy actor-critic","author":"degris","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553501"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"minh","year":"2016","journal-title":"Proc 33th Int Conf Mach Learn"},{"key":"ref17","first-page":"1","article-title":"Massively parallel methods for deep reinforcement learning","volume":"abs 1507 4296","author":"nair","year":"2015","journal-title":"CoRR"},{"key":"ref18","first-page":"1607","article-title":"Relative entropy policy search","author":"peters","year":"2010","journal-title":"Proc 24th AAAI Conf Artif Intell"},{"key":"ref19","first-page":"1583","article-title":"Online learning in episodic Markovian decision processes by relative entropy policy search","author":"zimin","year":"2013","journal-title":"Proc Int Conf Intell Robots Syst"},{"key":"ref28","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref4","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc 32th Int Conf Mach Learn"},{"key":"ref27","first-page":"1","article-title":"Efficient parallel methods for deep reinforcement learning","volume":"abs 1705 4862","author":"clemente","year":"2017","journal-title":"CoRR"},{"key":"ref3","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref6","first-page":"1889","article-title":"Opponent modeling in deep reinforcement learning","author":"he","year":"2016","journal-title":"Proc 33th Int Conf Mach Learn"},{"key":"ref5","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218596"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2020.3013599"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","author":"schulman","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref22","first-page":"1","article-title":"IMPACT: Importance weighted asynchronous architectures with clipped target networks","author":"luo","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref21","first-page":"1407","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn"},{"key":"ref24","first-page":"1","article-title":"Distributed prioritized experience replay","author":"horgan","year":"2018","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref23","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"journal-title":"Mathematical Methods of Statistics","year":"1946","author":"crem\u00e9r","key":"ref26"},{"key":"ref25","first-page":"4572","article-title":"Dimension-wise importance sampling weight clipping for sample-efficient reinforcement learning","author":"han","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09486881.pdf?arnumber=9486881","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,17]],"date-time":"2024-12-17T19:22:11Z","timestamp":1734463331000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9486881\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3097357","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}