{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:23:06Z","timestamp":1740169386135,"version":"3.37.3"},"reference-count":34,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1109\/access.2024.3402835","type":"journal-article","created":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:28:15Z","timestamp":1716226095000},"page":"71479-71491","source":"Crossref","is-referenced-by-count":0,"title":["An Efficient Distributed Reinforcement Learning Architecture for Long-Haul Communication Between Actors and Learner"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1690-6195","authenticated-orcid":false,"given":"Shin","family":"Morishima","sequence":"first","affiliation":[{"name":"Faculty of Engineering, Toyama Prefectural University, Toyama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-3842","authenticated-orcid":false,"given":"Hiroki","family":"Matsutani","sequence":"additional","affiliation":[{"name":"Graduate School of Science and Technology, Keio University, Yokohama, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","article-title":"QT-opt: Scalable deep reinforcement learning for vision-based robotic manipulation","author":"Kalashnikov","year":"2018","journal-title":"arXiv:1806.10293"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3054625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3102580"},{"key":"ref7","first-page":"1","article-title":"Distributed prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Horgan"},{"key":"ref8","article-title":"Massively parallel methods for deep reinforcement learning","author":"Nair","year":"2015","journal-title":"arXiv:1507.04296"},{"key":"ref9","first-page":"1","article-title":"Recurrent experience replay in distributed reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kapturowski"},{"key":"ref10","first-page":"1","article-title":"Never give up: Learning directed exploration strategies","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Badia"},{"key":"ref11","first-page":"507","article-title":"Agent57: Outperforming the Atari human benchmark","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Badia"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/PDP55904.2022.00020"},{"key":"ref13","article-title":"Suphx: Mastering mahjong with deep reinforcement learning","author":"Li","year":"2020","journal-title":"arXiv:2003.13590"},{"key":"ref14","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv:1912.06680"},{"key":"ref15","article-title":"Distributed deep reinforcement learning: A survey and a multi-player multi-agent learning toolbox","author":"Yin","year":"2022","journal-title":"arXiv:2212.00253"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3207346"},{"key":"ref17","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref18","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"Espeholt","year":"2018","journal-title":"arXiv:1802.01561"},{"key":"ref19","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul"},{"key":"ref20","article-title":"A deeper look at experience replay","author":"Zhang","year":"2017","journal-title":"arXiv:1712.01275"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6049"},{"key":"ref22","article-title":"Large batch experience replay","author":"Lahire","year":"2021","journal-title":"arXiv:2110.01528"},{"key":"ref23","first-page":"279","article-title":"Accelerating distributed reinforcement learning with in-switch computing","volume-title":"Proc. ACM\/IEEE 46th Annu. Int. Symp. Comput. Archit. (ISCA)","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428188"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3567445.3567454"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2938509"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2933761"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3247013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2924015"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759581"},{"key":"ref32","first-page":"1","article-title":"A framework of dual replay buffer: Balancing forgetting and generalization in reinforcement learning","volume-title":"Proc. Workshop Scaling Up Reinforcement Learn.","author":"Zhang"},{"volume-title":"OpenAI Gym","year":"2023","key":"ref33"},{"key":"ref34","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement learning","volume-title":"Proc. Int. Conf. Int. Conf. Mach. Learn.","volume":"48","author":"Wang"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10380310\/10534353.pdf?arnumber=10534353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,24]],"date-time":"2024-05-24T17:29:26Z","timestamp":1716571766000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10534353\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3402835","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}