{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:55:53Z","timestamp":1752231353766,"version":"3.37.3"},"reference-count":33,"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":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"Ministry of Science, ICT, through the Energy Cloud Research and Development Program","doi-asserted-by":"publisher","award":["2019M3F2A1073314"],"award-info":[{"award-number":["2019M3F2A1073314"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2020]]},"DOI":"10.1109\/access.2020.3012204","type":"journal-article","created":{"date-parts":[[2020,7,27]],"date-time":"2020-07-27T21:23:11Z","timestamp":1595884991000},"page":"137449-137461","source":"Crossref","is-referenced-by-count":12,"title":["Batch Prioritization in Multigoal Reinforcement Learning"],"prefix":"10.1109","volume":"8","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2862-6200","authenticated-orcid":false,"given":"Luiz Felipe","family":"Vecchietti","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1384-3459","authenticated-orcid":false,"given":"Taeyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6153-6541","authenticated-orcid":false,"given":"Kyujin","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1285-1454","authenticated-orcid":false,"given":"Junhee","family":"Hong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6949-1739","authenticated-orcid":false,"given":"Dongsoo","family":"Har","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref33","article-title":"Automatic goal generation for reinforcement learning agents","author":"florensa","year":"2017","journal-title":"arXiv 1705 06366"},{"key":"ref32","article-title":"Experienced deep reinforcement learning with generative adversarial networks (GANs) for model-free ultra reliable low latency communication","author":"kasgari","year":"2019","journal-title":"arXiv 1911 03264"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.06.022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8463162"},{"key":"ref10","article-title":"Prioritized experience replay","author":"schaul","year":"2015","journal-title":"arXiv 1511 05952"},{"key":"ref11","first-page":"7553","article-title":"Maximum entropy-regularized multi-goal reinforcement learning","author":"zhao","year":"2019","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref12","article-title":"Bias-reduced hindsight experience replay with virtual goal prioritization","author":"manela","year":"2019","journal-title":"arXiv 1905 05498"},{"key":"ref13","first-page":"5055","article-title":"Hindsight experience replay","author":"andrychowicz","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref14","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2015","journal-title":"arXiv 1509 02971"},{"key":"ref15","article-title":"OpenAI gym","author":"brockman","year":"2016","journal-title":"arXiv 1606 01540 [cs]"},{"key":"ref16","article-title":"Multi-goal reinforcement learning: Challenging robotics environments and request for research","author":"plappert","year":"2018","journal-title":"arXiv 1802 09464"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref18","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref19","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","volume":"24","author":"mccloskey","year":"1989","journal-title":"Psychol Learn Motivat"},{"key":"ref28","first-page":"113","article-title":"Energy-based hindsight experience prioritization","author":"zhao","year":"2018","journal-title":"Proc 2nd Conf Robot Learn"},{"key":"ref4","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"silver","year":"2017","journal-title":"arXiv 1712 01815"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/589"},{"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":"10.1109\/TCYB.2019.2890974"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2990722"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936863"},{"key":"ref2","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume":"48","author":"mnih","year":"2016","journal-title":"Proc 33rd Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992699"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1951.10500769"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2853582"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1001"},{"key":"ref23","article-title":"A deeper look at experience replay","author":"zhang","year":"2017","journal-title":"arXiv 1712 01275"},{"key":"ref26","first-page":"4851","article-title":"Remember and forget for experience replay","author":"novati","year":"2019","journal-title":"Proceedings 36th Int Conf Mach Learn"},{"key":"ref25","first-page":"347","article-title":"Experience selection in deep reinforcement learning for control","volume":"19","author":"de bruin","year":"2018","journal-title":"J Mach Learn Res"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/8948470\/09149884.pdf?arnumber=9149884","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T15:56:38Z","timestamp":1642002998000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9149884\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2020.3012204","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2020]]}}}