{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T17:05:41Z","timestamp":1792688741261,"version":"4.5.0"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2009057"],"award-info":[{"award-number":["2009057"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2022,9,1]]},"DOI":"10.1109\/tpds.2021.3134709","type":"journal-article","created":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T15:49:52Z","timestamp":1639410592000},"page":"2066-2078","source":"Crossref","is-referenced-by-count":16,"title":["PPOAccel: A High-Throughput Acceleration Framework for Proximal Policy Optimization"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6468-8623","authenticated-orcid":false,"given":"Yuan","family":"Meng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2062-1483","authenticated-orcid":false,"given":"Sanmukh","family":"Kuppannagari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajgopal","family":"Kannan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1609-8589","authenticated-orcid":false,"given":"Viktor","family":"Prasanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","year":"0"},{"key":"ref38","first-page":"265","article-title":"Tensorflow: A system for large-scale machine learning","author":"abadi","year":"2016","journal-title":"Proc 12th USENIX Symp Oper Syst Des Implementation"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056789"},{"key":"ref32","article-title":"Benchmarking model-based reinforcement learning","author":"langlois","year":"2019"},{"key":"ref31","year":"0"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240838"},{"key":"ref37","year":"0"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7056.001.0001"},{"key":"ref35","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Lear"},{"key":"ref34","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":"ref28","article-title":"A guide to convolution arithmetic for deep learning","author":"dumoulin","year":"2016"},{"key":"ref27","author":"nielsen","year":"2015","journal-title":"Neural Networks and Deep Learning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-1026-3"},{"key":"ref2","article-title":"Safe, multi-agent, reinforcement learning for autonomous driving","author":"shalev-shwartz","year":"2016"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0166-4115(97)80105-7"},{"key":"ref20","article-title":"IMPALA: Scalable distributed deep-RL with importance weighted actor-learner architectures","author":"espeholt","year":"0"},{"key":"ref22","article-title":"What matters in on-policy reinforcement learning? a large-scale empirical study","author":"andrychowicz","year":"2020"},{"key":"ref21","article-title":"RLlib: Abstractions for distributed reinforcement learning","author":"liang","year":"2018"},{"key":"ref24","year":"0"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref26","article-title":"An overview of gradient descent optimization algorithms","author":"ruder","year":"2016"},{"key":"ref25","article-title":"Dissecting the NVIDIA volta GPU architecture via microbenchmarking","author":"jia","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00012"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3039902.3039915"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/BF02055574"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref13","article-title":"OpenAI GYM","author":"brockman","year":"2016"},{"key":"ref14","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","author":"duan","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CIG.2018.8490422"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322259"},{"key":"ref17","year":"0"},{"key":"ref18","article-title":"Openai baselines","author":"dhariwal","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/1058129.1058148"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.metabol.2017.01.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2003.09.017"},{"key":"ref6","article-title":"Proximal policy optimization algorithms","author":"schulman","year":"2017"},{"key":"ref5","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","author":"sutton","year":"2000","journal-title":"Proc 12th Int Conf Advances Neural Inf Process Syst"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3174243.3174258"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ASAP.2019.00-24"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3295500.3356162"},{"key":"ref9","year":"0"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2019.00034"},{"key":"ref45","first-page":"107","article-title":"F-CNN: An FPGA-based framework for training convolutional neural networks","author":"zhao","year":"2016","journal-title":"Proc IEEE 27th Int Conf Appl -Specific Syst Archit Processors"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00013"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2885950"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/AERO.2017.7943929"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3301278"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3373087.3375359"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/9696253\/9647962-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/71\/9696253\/09647962.pdf?arnumber=9647962","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,25]],"date-time":"2022-04-25T17:10:02Z","timestamp":1650906602000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9647962\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"references-count":49,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2021.3134709","relation":{},"ISSN":["1045-9219","1558-2183","2161-9883"],"issn-type":[{"value":"1045-9219","type":"print"},{"value":"1558-2183","type":"electronic"},{"value":"2161-9883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,1]]}}}