{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T16:39:55Z","timestamp":1757608795181,"version":"3.44.0"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"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":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11127559","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"7930-7936","source":"Crossref","is-referenced-by-count":0,"title":["Learning Dexterous Bimanual Catch Skills Through Adversarial-Cooperative Heterogeneous-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Taewoo","family":"Kim","sequence":"first","affiliation":[{"name":"Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngwoo","family":"Yoon","sequence":"additional","affiliation":[{"name":"Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jaehong","family":"Kim","sequence":"additional","affiliation":[{"name":"Social Robotics Research Section, Electronics and Telecommunications Research Institute (ETRI),Daejeon,Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"doi-asserted-by":"publisher","key":"ref1","DOI":"10.15607\/RSS.2023.XIX.037"},{"key":"ref2","article-title":"Population based training of neural networks","author":"Jaderberg","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref3","first-page":"1887","article-title":"Dynamic handover: Throw and catch with bimanual hands","volume-title":"Conference on Robot Learning. PMLR","author":"Huang","year":"2023"},{"key":"ref4","article-title":"Dexcatch: Learning to catch arbitrary objects with dexterous hands","volume-title":"Conference on Robot Learning","author":"Lan","year":"2024"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TPAMI.2023.3339515"},{"doi-asserted-by":"publisher","key":"ref6","DOI":"10.1109\/TSMCC.2007.913919"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/978-3-642-14435-6_7"},{"doi-asserted-by":"publisher","key":"ref8","DOI":"10.1007\/978-3-030-60990-0_12"},{"key":"ref9","first-page":"242","article-title":"Multiagent reinforcement learning: theoretical framework and an algorithm","volume":"98","author":"Hu","year":"1998","journal-title":"ICML"},{"key":"ref10","first-page":"5571","article-title":"Mean field multi-agent reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Yang","year":"2018"},{"key":"ref11","article-title":"Safe, multiagent, reinforcement learning for autonomous driving","author":"Shalev-Shwartz","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref12","article-title":"Multi-agent reinforcement learning for autonomous driving: A survey","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1007\/978-3-319-71682-4_5"},{"issue":"2020","key":"ref14","article-title":"Deep multi-agent reinforcement learning for decentralized continuous cooperative control","volume":"19","author":"de Witt","journal-title":"arXiv preprint arXiv"},{"volume-title":"Universal robots ur3","year":"2024","author":"Robots","key":"ref15"},{"volume-title":"Allegro hand technical information","year":"2024","author":"Hand","key":"ref16"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/ICAR.2015.7251504"},{"issue":"1\u201367","key":"ref18","first-page":"1","article-title":"Heterogeneous-agent reinforcement learning","volume":"25","author":"Zhong","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref19","article-title":"Fast and accurate deep network learning by exponential linear units (elus)","author":"Clevert","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"D2rl: Deep dense architectures in reinforcement learning","author":"Sinha","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref22","article-title":"Isaac gym: High performance gpu based physics simulation for robot learning","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks","author":"Makoviychuk","year":"2021"},{"volume-title":"rl-games: A high-performance framework for reinforcement learning","year":"2021","author":"Makoviichuk","key":"ref23"},{"key":"ref24","volume-title":"Mind in society: The development of higher psychological processes","volume":"86","author":"Vygotsky","year":"1978"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.7551\/mitpress\/4561.003.0011"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","start":{"date-parts":[[2025,5,19]]},"location":"Atlanta, GA, USA","end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11127559.pdf?arnumber=11127559","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:45:32Z","timestamp":1756881932000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11127559\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11127559","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}