{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:26Z","timestamp":1740169226479,"version":"3.37.3"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Major Project of the New Generation of Artificial Intelligence, China","award":["2018AAA0102900"],"award-info":[{"award-number":["2018AAA0102900"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3045835","type":"journal-article","created":{"date-parts":[[2020,12,18]],"date-time":"2020-12-18T21:08:15Z","timestamp":1608325695000},"page":"228099-228107","source":"Crossref","is-referenced-by-count":1,"title":["Policy Return: A New Method for Reducing the Number of Experimental Trials in Deep Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9006-4520","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"first","affiliation":[{"name":"State Key Laboratory of VR Technology & Systems, Beihang University (BUAA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2934-9033","authenticated-orcid":false,"given":"Shuling","family":"Dai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of VR Technology & Systems, Beihang University (BUAA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4557-9066","authenticated-orcid":false,"given":"Yongjia","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of VR Technology & Systems, Beihang University (BUAA), Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref31","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761663"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900530"},{"key":"ref12","article-title":"Deep reinforcement learning that matters","author":"henderson","year":"2017","journal-title":"arXiv 1709 06560"},{"key":"ref13","article-title":"Deep reinforcement learning and the deadly triad","author":"van hasselt","year":"2018","journal-title":"arXiv 1812 02648"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref15","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref16","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","article-title":"Emergence of locomotion behaviours in rich environments","author":"heess","year":"2017","journal-title":"arXiv 1707 02286"},{"key":"ref18","article-title":"How many random seeds? Statistical power analysis in deep reinforcement learning experiments","author":"colas","year":"2018","journal-title":"arXiv 1806 08295"},{"key":"ref19","first-page":"5","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref28","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017","journal-title":"arXiv 1707 06347"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of go without human knowledge","volume":"550","author":"silver","year":"2017","journal-title":"Nature"},{"key":"ref27","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref3","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":"ref6","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref29","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","article-title":"End-to-end training of deep visuomotor policies","author":"levine","year":"2015","journal-title":"Arxiv 1504 00702"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202134"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3005745.3005750"},{"key":"ref1","article-title":"Playing Atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"arXiv 1312 5602"},{"key":"ref20","article-title":"Noisy networks for exploration","author":"fortunato","year":"2017","journal-title":"arXiv 1706 10295"},{"key":"ref22","article-title":"A distributional perspective on reinforcement learning","author":"bellemare","year":"2017","journal-title":"arXiv 1707 06887"},{"key":"ref21","article-title":"Rainbow: Combining improvements in deep reinforcement learning","author":"hessel","year":"2017","journal-title":"arXiv 1710 02298"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-00031-1_4"},{"key":"ref23","first-page":"3","author":"sutton","year":"1998","journal-title":"Introduction to Reinforcement Learning"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/S0019-9958(58)80003-0"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09298771.pdf?arnumber=9298771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T19:59:38Z","timestamp":1662667178000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9298771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3045835","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}