{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T15:43:05Z","timestamp":1769269385029,"version":"3.49.0"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T00:00:00Z","timestamp":1743379200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,3,31]]},"DOI":"10.23919\/date64628.2025.10992886","type":"proceedings-article","created":{"date-parts":[[2025,5,21]],"date-time":"2025-05-21T17:36:35Z","timestamp":1747848995000},"page":"1-7","source":"Crossref","is-referenced-by-count":2,"title":["PEARL: FPGA-Based Reinforcement Learning Acceleration with Pipelined Parallel Environments"],"prefix":"10.23919","author":[{"given":"Jiayi","family":"Li","sequence":"first","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongxiao","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenshuo","family":"Yue","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yihan","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daijing","family":"Shi","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anjunyi","family":"Fan","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchao","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bonan","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref2","article-title":"MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning","volume-title":"Conference on Neural Information Processing Systems (NeruIPS)","author":"Ma","year":"2024"},{"key":"ref3","article-title":"RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Yuan","year":"2024"},{"key":"ref4","article-title":"Envpool: A Highly Parallel Reinforcement Learning Environment Execution Engine","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Weng","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116248"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.23919\/DATE58400.2024.10546530"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2018.8342120"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11757"},{"key":"ref9","author":"Schulman","year":"2017","journal-title":"Proximal Policy Optimization Algorithms"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.31096\/wua9999-wp_0551_box_5"},{"key":"ref11","article-title":"Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning","volume-title":"International conference on machine learning (ICML)","author":"Petrenko","year":"2020"},{"key":"ref12","author":"Hessel","year":"2021","journal-title":"Podracer Architectures for Scalable Reinforcement Learning"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2008.05.014"},{"key":"ref14","article-title":"WarpDrive: Fast End-to-End Deep Multi-Agent Reinforcement Learning on a GPU","author":"Lan","year":"2022","journal-title":"Journal of Machine Learning Research (JMLR)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM60383.2024.00020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1142\/S0129626411000151"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICFPT59805.2023.00048"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2004.46"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/date.2009.5090727"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.23919\/DATE48585.2020.9116362"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.23919\/DATE56975.2023.10137303"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2010.79"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref24","article-title":"Efficient Memory-based Learning for Robot Control","author":"Moore","year":"1990","journal-title":"University of Cambridge, Computer Laboratory, Tech. Rep."},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnn.1998.712192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1613\/jair.639"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3912"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.23919\/FPL.2017.8056826"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/FPT.2018.00064"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW63119.2024.00023"},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.3850\/9783981537079_1021","article-title":"ECOSCALE: Reconfigurable computing and runtime system for future exascale systems","volume-title":"Design, Automation & Test in Europe Conference & Exhibition (DATE)","author":"Mavroidis","year":"2016"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/FPL.2019.00021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304058"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM48280.2020.00012"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1145\/3400302.3415636","article-title":"A Many-Core Accelerator Design for On-Chip Deep Reinforcement Learning","volume-title":"International Conference on Computer-Aided Design (ICCAD)","author":"Wang","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18074.2021.9586213"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549437"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPSW52791.2021.00022"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/FPL57034.2022.00023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3528416.3530227"}],"event":{"name":"2025 Design, Automation & Test in Europe Conference (DATE)","location":"Lyon, France","start":{"date-parts":[[2025,3,31]]},"end":{"date-parts":[[2025,4,2]]}},"container-title":["2025 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10992638\/10992588\/10992886.pdf?arnumber=10992886","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T05:32:22Z","timestamp":1747891942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10992886\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,31]]},"references-count":40,"URL":"https:\/\/doi.org\/10.23919\/date64628.2025.10992886","relation":{},"subject":[],"published":{"date-parts":[[2025,3,31]]}}}