{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T05:40:01Z","timestamp":1745559601420,"version":"3.40.4"},"reference-count":38,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62293545","62425117","62206155"],"award-info":[{"award-number":["62293545","62425117","62206155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2024T170497"],"award-info":[{"award-number":["2024T170497"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"China Postdoctoral Innovation Talents Support Program","award":["BX20230184"],"award-info":[{"award-number":["BX20230184"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/lra.2025.3557224","type":"journal-article","created":{"date-parts":[[2025,4,3]],"date-time":"2025-04-03T00:24:20Z","timestamp":1743639860000},"page":"5497-5504","source":"Crossref","is-referenced-by-count":0,"title":["ArenaSim: A High-Performance Simulation Platform for Multi-Robot Self-Play Learning"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-2731-4507","authenticated-orcid":false,"given":"Yuxin","family":"Ke","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9650-8874","authenticated-orcid":false,"given":"Shaohui","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8061-7486","authenticated-orcid":false,"given":"Zhi","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-9585","authenticated-orcid":false,"given":"Haoran","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5216-3181","authenticated-orcid":false,"given":"Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6111-340X","authenticated-orcid":false,"given":"You","family":"He","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"article-title":"Deep reinforcement learning from self-play in imperfect-information games","year":"2016","author":"Heinrich","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/science.aam6960"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Berner","key":"ref7"},{"key":"ref8","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"Proc. 18th Int. Conf. Auton. Agents MultiAgent Syst.","author":"Samvelyan","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2015.7414623"},{"key":"ref10","article-title":"Emergent tool use from multi-agent autocurricula","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Baker","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191291"},{"year":"2021","key":"ref13","article-title":"RoboMaster University AI Challenge"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2004.1389727"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-91590-6_1"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"article-title":"Fever basketball: A complex, flexible, and asynchronized sports game environment for multi-agent reinforcement learning","year":"2020","author":"Jia","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00861-3"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2023.3259724"},{"key":"ref20","article-title":"MAESTRO: Open-ended environment design for multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Samvelyan","year":"2023"},{"key":"ref21","first-page":"27862","article-title":"Mate: Benchmarking multi-agent reinforcement learning in distributed target coverage control","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Pan","year":"2022"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1147\/rd.33.0210"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3058898"},{"key":"ref24","first-page":"434","article-title":"Open-ended learning in symmetric zero-sum games","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Balduzzi","year":"2019"},{"key":"ref25","first-page":"17443","article-title":"Real world games look like spinning tops","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Czarnecki","year":"2020"},{"key":"ref26","first-page":"4193","article-title":"A unified game-theoretic approach to multiagent reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Lanctot","year":"2017"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/880"},{"key":"ref28","first-page":"67771","article-title":"Policy space diversity for non-transitive games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Yao","year":"2023"},{"key":"ref29","article-title":"Mastering Xiangqi by tackling non-transitivity in two-player zero-sum games","volume-title":"Trans. Mach. Learn. Res.","author":"Li","year":"2023"},{"key":"ref30","article-title":"A generalized training approach for multiagent learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Muller","year":"2020"},{"key":"ref31","article-title":"Emergent complexity via multi-agent competition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bansal","year":"2018"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1426-8"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3618397"},{"year":"2025","key":"ref34","article-title":"NVIDIA ISAAC sim"},{"key":"ref35","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Proc. 5th Conf. Robot Learn.","volume":"164","author":"Rudin","year":"2022"},{"key":"ref36","first-page":"1722","article-title":"In-hand object rotation via rapid motor adaptation","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Qi","year":"2023"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref37"},{"key":"ref38","first-page":"24611","article-title":"The surprising effectiveness of PPO in cooperative multi-agent games","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu","year":"2022"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/10969146\/10947320.pdf?arnumber=10947320","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T05:27:25Z","timestamp":1745558845000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947320\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":38,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/lra.2025.3557224","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"type":"electronic","value":"2377-3766"},{"type":"electronic","value":"2377-3774"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}