{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T18:34:18Z","timestamp":1785954858512,"version":"3.56.0"},"reference-count":30,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T00:00:00Z","timestamp":1646092800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Institute of Information and Communications Technology Planning and Evaluation"},{"DOI":"10.13039\/501100003621","name":"Korea Government (MSIT)","doi-asserted-by":"publisher","award":["2020-0-00440"],"award-info":[{"award-number":["2020-0-00440"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cybern."],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1109\/tcyb.2020.2990722","type":"journal-article","created":{"date-parts":[[2020,5,21]],"date-time":"2020-05-21T21:23:36Z","timestamp":1590096216000},"page":"1515-1526","source":"Crossref","is-referenced-by-count":41,"title":["Sampling Rate Decay in Hindsight Experience Replay for Robot Control"],"prefix":"10.1109","volume":"52","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2862-6200","authenticated-orcid":false,"given":"Luiz Felipe","family":"Vecchietti","sequence":"first","affiliation":[{"name":"Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0841-5190","authenticated-orcid":false,"given":"Minah","family":"Seo","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6949-1739","authenticated-orcid":false,"given":"Dongsoo","family":"Har","sequence":"additional","affiliation":[{"name":"Cho Chun Shik Graduate School of Green Transportation, Korea Advanced Institute of Science and Technology, Daejeon, South Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature16961"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"issue":"1","key":"ref4","first-page":"1334","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2890974"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref9","volume-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2853582"},{"key":"ref11","volume-title":"A deeper look at experience replay","author":"Zhang","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref13","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn. (ICML)","author":"Zhao"},{"issue":"9","key":"ref14","first-page":"1","article-title":"Experience selection in deep reinforcement learning for control","volume":"19","author":"de Bruin","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref16","first-page":"5055","article-title":"Hindsight experience replay","volume-title":"Proc. 31st Conf. Neural Inf. Process. Syst. (NIPS)","author":"Andrychowicz"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref19","volume-title":"Learning to execute","author":"Zaremba","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/nature20101"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2013.00313"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2790981"},{"key":"ref23","volume-title":"Intrinsic motivation and automatic curricula via asymmetric self-play","author":"Sukhbaatar","year":"2017"},{"key":"ref24","first-page":"1514","article-title":"Automatic goal generation for reinforcement learning agents","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Florensa"},{"key":"ref25","volume-title":"ARCHER: Aggressive rewards to counter bias in hindsight experience replay","author":"Lanka","year":"2018"},{"key":"ref26","article-title":"The importance of experience replay database composition in deep reinforcement learning","volume-title":"Deep Reinforcement Learn. Workshop Conf. Neural Inf. Process. Syst. (NIPS)","author":"de Bruin"},{"key":"ref27","volume-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"Plappert","year":"2018"},{"key":"ref28","volume-title":"OpenAI Gym","author":"Brockman","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref30","volume-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"}],"container-title":["IEEE Transactions on Cybernetics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6221036\/9733099\/09098063.pdf?arnumber=9098063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:21:39Z","timestamp":1704838899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9098063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3]]},"references-count":30,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcyb.2020.2990722","relation":{},"ISSN":["2168-2267","2168-2275"],"issn-type":[{"value":"2168-2267","type":"print"},{"value":"2168-2275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3]]}}}