{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T11:40:57Z","timestamp":1774352457524,"version":"3.50.1"},"reference-count":42,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"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":["CNS-2009057"],"award-info":[{"award-number":["CNS-2009057"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["SPX-2333009"],"award-info":[{"award-number":["SPX-2333009"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100002418","name":"Intel Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DEVCOM Army Research Lab","award":["W911NF2220159"],"award-info":[{"award-number":["W911NF2220159"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Parallel Distrib. Syst."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpds.2025.3566766","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T17:45:49Z","timestamp":1747071949000},"page":"1401-1415","source":"Crossref","is-referenced-by-count":3,"title":["An Acceleration Framework for Deep Reinforcement Learning Using Heterogeneous Systems"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6468-8623","authenticated-orcid":false,"given":"Yuan","family":"Meng","sequence":"first","affiliation":[{"name":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}]},{"given":"Mahesh A.","family":"Iyer","sequence":"additional","affiliation":[{"name":"Altera Corporation, San Jose, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1609-8589","authenticated-orcid":false,"given":"Viktor K.","family":"Prasanna","sequence":"additional","affiliation":[{"name":"Ming Hsieh Department of Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202137"},{"key":"ref2","article-title":"AlphaStar: Mastering the real-time strategy game StarCraft II","volume":"2","author":"Vinyals","year":"2019","journal-title":"DeepMind Blog"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC53243.2021.00014"},{"key":"ref4","article-title":"Ray RLlib: A composable and scalable reinforcement learning library","author":"Liang","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00012"},{"key":"ref8","article-title":"PGAbB: A block-based graph processing framework for heterogeneous platforms","author":"Yasar","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2012.47"},{"key":"ref10","article-title":"A software-hardware co-optimized toolkit for deep reinforcement learning on heterogeneous platforms","author":"Meng","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3097276"},{"key":"ref12","article-title":"Prioritized experience replay","author":"Schaul","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11796"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2023.3264823"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729586"},{"key":"ref16","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref18","first-page":"1329","article-title":"Benchmarking deep reinforcement learning for continuous control","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Duan"},{"key":"ref19","article-title":"AMD heterogeneous accelerated compute clusters","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2021.3088549"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480101"},{"key":"ref22","article-title":"Distributed prioritized experience replay","author":"Horgan","year":"2018"},{"key":"ref23","article-title":"DI-engine: A universal AI system\/engine for decision intelligence","author":"Niu","year":"2021"},{"key":"ref24","article-title":"Massively parallel methods for deep reinforcement learning","author":"Nair","year":"2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.5220\/0001143902220229"},{"key":"ref26","first-page":"279","article-title":"Accelerating distributed reinforcement learning with in-switch computing","volume-title":"Proc. 46th Int. Symp. Comput. Archit.","author":"Li"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3210377.3210394"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3528416.3530227"},{"key":"ref29","first-page":"977","article-title":"MSRL: Distributed reinforcement learning with dataflow fragments","volume-title":"Proc. USENIX Annu. Tech. Conf.","author":"Zhu"},{"key":"ref30","article-title":"NVLink","year":"2025"},{"key":"ref31","first-page":"219","article-title":"PyTorch RPC: Distributed deep learning built on tensor-optimized remote procedure calls","volume-title":"Proc. 6th Conf. Mach. Learn. Syst.","author":"Damania"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/71.993206"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-016-1917-2"},{"key":"ref35","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"},{"key":"ref36","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Paszke"},{"key":"ref38","article-title":"Intel oneAPI","year":"2022"},{"key":"ref39","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref40","article-title":"Gymnasium: A standard interface for reinforcement learning environments","author":"Towers","year":"2024"},{"key":"ref41","first-page":"1","article-title":"Stable-baselines3: Reliable reinforcement learning implementations","volume-title":"J. Mach. Learn. Res.","volume":"22","author":"Raffin","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3431920.3439290"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3543622.3573177"},{"key":"ref44","first-page":"316","article-title":"Online sparse reinforcement learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Hao"}],"container-title":["IEEE Transactions on Parallel and Distributed Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/71\/11008439\/11002648-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/71\/11008439\/11002648.pdf?arnumber=11002648","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,26]],"date-time":"2025-05-26T18:07:11Z","timestamp":1748282831000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11002648\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":42,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpds.2025.3566766","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":[[2025,7]]}}}