{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:21Z","timestamp":1766068101023,"version":"3.32.0"},"reference-count":44,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10801682","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"5918-5924","source":"Crossref","is-referenced-by-count":4,"title":["MQE: Unleashing the Power of Interaction with Multi-agent Quadruped Environment"],"prefix":"10.1109","author":[{"given":"Ziyan","family":"Xiong","sequence":"first","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,AI Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhipu AI,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei-Wei","family":"Tu","sequence":"additional","affiliation":[{"name":"4Paradigm Inc.,Beijing,China,100084"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaofeng","family":"He","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,AI Institute,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Institute for Interdisciplinary Information Sciences,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","year":"2021","author":"Makoviychuk","key":"ref1"},{"key":"ref2","first-page":"91","article-title":"Learning to walk in minutes using massively parallel deep reinforcement learning","volume-title":"Conference on Robot Learning","author":"Rudin"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abc5986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abk2822"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/e26010093"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9981984"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160325"},{"article-title":"Learning a unified policy for whole-body control of manipulation and locomotion","volume-title":"6th Annual Conference on Robot Learning","author":"Fu","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18178\/ijeetc.12.5.317-325"},{"issue":"02","key":"ref10","first-page":"63","article-title":"Artificial intelligence application in smart warehousing environment for automated logistics","volume":"1","author":"Pandian","year":"2019","journal-title":"Journal of Artificial Intelligence"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/4384954"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/app11031209"},{"key":"ref13","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.11.054"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"article-title":"Tizero: Mastering multi-agent football with curriculum learning and self-play","year":"2023","author":"Lin","key":"ref16"},{"article-title":"The star-craft multi-agent challenge","year":"2019","author":"Samvelyan","key":"ref17"},{"key":"ref18","first-page":"403","article-title":"Legged locomotion in challenging terrains using egocentric vision","volume-title":"Conference on robot learning","author":"Agarwal"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2979660"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00576-3"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aau5872"},{"key":"ref22","first-page":"02783649231224053","article-title":"Rapid locomotion via reinforcement learning","author":"Margolis","year":"2022","journal-title":"The International Journal of Robotics Research"},{"article-title":"Extreme parkour with legged robots","year":"2023","author":"Cheng","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460731"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.2006.1642158"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2019.2958207"},{"article-title":"Emergence of locomotion behaviours in rich environments","year":"2017","author":"Heess","key":"ref27"},{"article-title":"Learning to walk via deep reinforcement learning","year":"2018","author":"Haarnoja","key":"ref28"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67361-5_40"},{"key":"ref30","first-page":"1147","article-title":"Flightmare: A flexible quadrotor simulator","volume-title":"Conference on Robot Learning","author":"Song"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3301273"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339515"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref34","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref35"},{"article-title":"Qplex: Duplex dueling multi-agent q-learning","year":"2020","author":"Wang","key":"ref36"},{"key":"ref37","first-page":"24611","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","volume":"35","author":"Yu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Multi-agent reinforcement learning is a sequence modeling problem","year":"2022","author":"Wen","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2021.103997"},{"article-title":"Learning graph-enhanced commander-executor for multi-agent navigation","year":"2023","author":"Yang","key":"ref40"},{"article-title":"Deep reinforcement learning for real autonomous mobile robot navigation in indoor environments","year":"2020","author":"Surmann","key":"ref41"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3356168"},{"key":"ref43","first-page":"22","article-title":"Walk these ways: Tuning robot control for generalization with multiplicity of behavior","volume-title":"Conference on Robot Learning","author":"Margolis"},{"article-title":"Openrl: A unified reinforcement learning framework","year":"2023","author":"Huang","key":"ref44"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10801682.pdf?arnumber=10801682","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T06:57:58Z","timestamp":1735196278000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10801682\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10801682","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}