{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T13:53:54Z","timestamp":1752674034192,"version":"3.37.3"},"reference-count":28,"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\/"}],"funder":[{"name":"Research and Development Fund for Young Teachers of Southeast University Chengxian College","award":["Z0057"],"award-info":[{"award-number":["Z0057"]}]},{"DOI":"10.13039\/501100012216","name":"Jiangsu Provincial University Philosophy and Social Science Research Project","doi-asserted-by":"publisher","award":["2022SJYB0707"],"award-info":[{"award-number":["2022SJYB0707"]}],"id":[{"id":"10.13039\/501100012216","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3441242","type":"journal-article","created":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T17:27:34Z","timestamp":1723224454000},"page":"117737-117744","source":"Crossref","is-referenced-by-count":2,"title":["Massively High-Throughput Reinforcement Learning for Classic Control on GPUs"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3301-4523","authenticated-orcid":false,"given":"Xuan","family":"Sha","sequence":"first","affiliation":[{"name":"School of Civil and Transportation Engineering, Southeast University Chengxian College, Nanjing, Jiangsu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6857-6804","authenticated-orcid":false,"given":"Tian","family":"Lan","sequence":"additional","affiliation":[{"name":"Salesforce AI Research, Palo Alto, CA, USA"}]}],"member":"263","reference":[{"volume-title":"Artificial Intelligence: A Modern Approach","year":"2016","author":"Russell","key":"ref1"},{"volume-title":"OpenAI Five","year":"2018","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989385"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920987859"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-023-10620-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abk2607"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3900237"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1021\/jacs.1c08794"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1051\/0004-6361\/202243311"},{"key":"ref11","first-page":"5026","article-title":"MuJoCo: A physics engine for modelbased control","volume-title":"Proc. IEEE\/RSJ Int. Conf. Intell. Robots Syst.","author":"Todorov"},{"key":"ref12","article-title":"Continuous control with deep reinforcement learning","author":"Lillicrap","year":"2015","journal-title":"arXiv:1509.02971"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/taes.2022.3218496"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s42241-020-0028-y"},{"key":"ref15","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv:1602.01783"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1137\/19m1288012"},{"issue":"316","key":"ref17","first-page":"1","article-title":"WarpDrive: Fast end-to-end deep multi-agent reinforcement learning on a GPU","volume":"23","author":"Lan","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","article-title":"Mava: A research library for distributed multi-agent reinforcement learning in JAX","author":"de Kock","year":"2021","journal-title":"arXiv:2107.01460"},{"key":"ref19","article-title":"Acme: A research framework for distributed reinforcement learning","author":"Hoffman","year":"2020","journal-title":"arXiv:2006.00979"},{"key":"ref20","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actorlearner architectures","author":"Espeholt","year":"2018","journal-title":"arXiv:1802.01561"},{"journal-title":"EvoJAX: Hardware-Accelerated Neuroevolution","year":"2022","author":"Tang","key":"ref21"},{"key":"ref22","article-title":"Podracer architectures for scalable reinforcement learning","author":"Hessel","year":"2021","journal-title":"arXiv:2104.06272"},{"key":"ref23","article-title":"Accelerating reinforcement learning through GPU Atari emulation","author":"Dalton","year":"2019","journal-title":"arXiv:1907.08467"},{"key":"ref24","article-title":"Brax\u2014A differentiable physics engine for large scale rigid body simulation","author":"Daniel Freeman","year":"2021","journal-title":"arXiv:2106.13281"},{"key":"ref25","article-title":"Isaac gym: High performance GPU-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv:2108.10470"},{"key":"ref26","article-title":"WarpDrive: Extremely fast end-to-end deep multi-agent reinforcement learning on a GPU","author":"Lan","year":"2021","journal-title":"arXiv:2108.13976"},{"key":"ref27","article-title":"OpenAI gym","author":"Brockman","year":"2016","journal-title":"arXiv:1606.01540"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2833157.2833162"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10632139.pdf?arnumber=10632139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T04:10:20Z","timestamp":1725163820000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10632139\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3441242","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2024]]}}}