{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:56:29Z","timestamp":1759334189071,"version":"build-2065373602"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,17]],"date-time":"2025-08-17T00:00:00Z","timestamp":1755388800000},"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":[[2025,8,17]]},"DOI":"10.1109\/case58245.2025.11163870","type":"proceedings-article","created":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T17:24:07Z","timestamp":1758648247000},"page":"1231-1238","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Population-Based Reinforcement Learning across Robotic Tasks with GPU-Accelerated Simulation"],"prefix":"10.1109","author":[{"given":"Asad","family":"Ali Shahid","sequence":"first","affiliation":[{"name":"Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yashraj","family":"Narang","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincenzo","family":"Petrone","sequence":"additional","affiliation":[{"name":"Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrico","family":"Ferrentino","sequence":"additional","affiliation":[{"name":"University of Salerno,Fisciano,Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Handa","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dieter","family":"Fox","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation,Santa Clara,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco","family":"Pavone","sequence":"additional","affiliation":[{"name":"Stanford University,Stanford,CA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Loris","family":"Roveda","sequence":"additional","affiliation":[{"name":"Dalle Molle Institute for Artificial Intelligence, IDSIA USI-SUPSI"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"article-title":"Dota 2 with Large Scale Deep Reinforcement Learning","year":"2019","author":"Berner","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app112110227"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.035"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-022-10034-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460655"},{"article-title":"Accelerated Policy Learning with Parallel Differentiable Simulation","volume-title":"Proc. Int. Conf. Learn. Represent","author":"Xu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.039"},{"article-title":"Solving Rubik\u2019s Cube with a Robot Hand","year":"2019","author":"Akkaya","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"article-title":"Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning","year":"2021","author":"Makoviychuk","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160216"},{"key":"ref15","first-page":"270","article-title":"GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learning","volume-title":"Proc. Conf. Robot Learn","volume":"87","author":"Liang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981458"},{"key":"ref17","first-page":"91","article-title":"Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning","volume-title":"Proc. Conf. Robot Learn","volume":"164","author":"Rudin"},{"article-title":"Proximal Policy Optimization Algorithms","year":"2017","author":"Schulman","key":"ref18"},{"key":"ref19","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","volume":"80","author":"Haarnoja"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.32657\/10356\/90191"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aau6249"},{"key":"ref23","first-page":"6533","article-title":"Fast Population-Based Reinforcement Learning on a Single Machine","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"162","author":"Flajolet"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref25","first-page":"487","article-title":"Interactions Between Learning and Evolution","volume":"10","author":"Ackley","year":"1991","journal-title":"Artif. Life II"},{"article-title":"Population Based Training of Neural Networks","year":"2017","author":"Jaderberg","key":"ref26"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.037"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3546126"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3544083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2025.3540391"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2024.3505784"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.016"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref35","first-page":"19 440","article-title":"Parallel Q-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation","volume-title":"Proc. Int. Conf. Mach. Learn","volume":"202","author":"Li"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/EVCO_a_00025"},{"key":"ref37","first-page":"17 200","article-title":"Provably Efficient Online Hyperparameter Optimization with Population-Based Bandits","volume-title":"Proc. Adv. Neural Inform. Process. Syst","volume":"33","author":"Parker-Holder"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/70.760350"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JRA.1987.1087068"},{"article-title":"Faster Improvement Rate Population Based Training","year":"2021","author":"Dalibard","key":"ref41"}],"event":{"name":"2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)","start":{"date-parts":[[2025,8,17]]},"location":"Los Angeles, CA, USA","end":{"date-parts":[[2025,8,21]]}},"container-title":["2025 IEEE 21st International Conference on Automation Science and Engineering (CASE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11163731\/11163732\/11163870.pdf?arnumber=11163870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T13:41:58Z","timestamp":1759239718000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11163870\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,17]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/case58245.2025.11163870","relation":{},"subject":[],"published":{"date-parts":[[2025,8,17]]}}}