{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:27:14Z","timestamp":1770917234949,"version":"3.50.1"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,18]],"date-time":"2023-06-18T00:00:00Z","timestamp":1687046400000},"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 (NSFC)","doi-asserted-by":"publisher","award":["62103409,62136008"],"award-info":[{"award-number":["62103409,62136008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,18]]},"DOI":"10.1109\/ijcnn54540.2023.10191291","type":"proceedings-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:30:03Z","timestamp":1690997403000},"page":"1-8","source":"Crossref","is-referenced-by-count":9,"title":["NeuronsMAE: A Novel Multi-Agent Reinforcement Learning Environment for Cooperative and Competitive Multi-Robot Tasks"],"prefix":"10.1109","author":[{"given":"Guangzheng","family":"Hu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}]},{"given":"Haoran","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation,Beijing,China"}]},{"given":"Shasha","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences,Beijing,China"}]},{"given":"Yuanheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation,Beijing,China"}]},{"given":"Dongbin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2018.2823329"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"key":"ref4","article-title":"Value-decomposition networks for cooperative multi -agent learning based on team reward","volume-title":"International Conference on Autonomous Agents and Multiagent Systems (AAMAS)","author":"Sunehag"},{"key":"ref5","first-page":"4295","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning (ICML)","author":"Rashid"},{"key":"ref6","article-title":"The surprising effectiveness of ppo in cooperative, multi-agent games","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Trust region policy optimisation in multi-agent rein-forcement learning","author":"Kuba","year":"2021","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"2186","article-title":"The starcraft multi-agent challenge","volume-title":"In-ternational Conference on Autonomous Agents and MultiAgent Systems (AAMAS)","author":"Samvelyan"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121546"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105869"},{"key":"ref12","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","volume":"34","author":"Peng","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref13","article-title":"Multi-agent constrained policy optimisation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","first-page":"6382","article-title":"Multi-agent actor-critic for mixed cooperative-competitive en-vironments","volume-title":"International Conference on Neural Information Processing Systems (NeurIPS)","author":"Lowe"},{"key":"ref15","article-title":"Unity: A general platform for intelligent agents","author":"Juliani","year":"2018","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11371"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561491"},{"key":"ref18","first-page":"103","article-title":"Learning a decentralized multi-arm motion planner","volume-title":"Conference on Robot Learning","author":"Ha"},{"key":"ref19","article-title":"Multirobolearn: An open-source framework for multi-robot deep reinforcement learning","author":"Chen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"From multi-agent to multi-robot: A scalable training and evaluation platform for multi-robot reinforcement learning","author":"Liang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2927869"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179775"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3041469"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561105"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9811950"},{"key":"ref27","article-title":"A framework for studying reinforcement learning and sim-to-real in robot soccer","author":"Bassani","year":"2020","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3010732"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/SII46433.2020.9025987"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968201"},{"key":"ref31","article-title":"Neurons-Gym: A hybrid framework and benchmark for robot tasks with sim2real policy learning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/S0031-3203(02)00060-2"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref34","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1724-z"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","location":"Gold Coast, Australia","start":{"date-parts":[[2023,6,18]]},"end":{"date-parts":[[2023,6,23]]}},"container-title":["2023 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10190990\/10190992\/10191291.pdf?arnumber=10191291","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T02:42:18Z","timestamp":1710384138000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191291\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191291","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}