{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T17:00:05Z","timestamp":1770742805437,"version":"3.49.0"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,8]],"date-time":"2024-07-08T00:00:00Z","timestamp":1720396800000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,8]]},"DOI":"10.1109\/icarm62033.2024.10715990","type":"proceedings-article","created":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T17:27:32Z","timestamp":1729272452000},"page":"837-842","source":"Crossref","is-referenced-by-count":1,"title":["Dynamic Formation Planning and Control for Robot Soccer Game with Multi-Agent Reinforcement Learning and Behavioral Model"],"prefix":"10.1109","author":[{"given":"Haier","family":"Zhu","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China,518055"}]},{"given":"Hanzhong","family":"Zhong","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}]},{"given":"Bo","family":"Yan","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School,Shenzhen,China,518055"}]},{"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Automation,Beijing,China,100084"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/HICSS.2004.1265190"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2016.05.127"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1049\/iet-its.2009.0070"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-021-00048-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1631\/FITEE.2200055"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1080\/10798587.2000.10768155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v18i1.1276"},{"key":"ref8","first-page":"181","article-title":"Simspark-concepts and application in the robocup 3d soccer simulation league","volume":"174","author":"Boedecker","year":"2008","journal-title":"Auton. Rob"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-25940-4_40"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1142\/9789814343312_0001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3075065"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCITECHN.2008.4803107"},{"key":"ref13","first-page":"7","article-title":"Formal behavior specification of multi-robot systems using hierarchical state machines in xabsl","volume-title":"AAMASO8-workshop on formal models and methods for multi-robot systems","author":"Risler"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-021-00768-8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1017\/S0269888912000057"},{"key":"ref16","first-page":"1146","article-title":"Stabilising experience replay for deep multiagent reinforcement learning","volume-title":"International conference on machine learning. PMLR","author":"Foerster"},{"key":"ref17","article-title":"Lenient multiagent deep reinforcement learning","author":"Palmer","year":"2017","journal-title":"arXiv preprint arXiv:1707.04402"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97310-4_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref20","first-page":"459","article-title":"Cooperative multi-agent policy gradient","volume-title":"Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2018","author":"Bono"},{"key":"ref21","article-title":"Inequity aversion improves cooperation in intertemporal social dilemmas","volume":"31","author":"Hughes","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst"},{"issue":"1","key":"ref22","first-page":"7234","article-title":"Monotonic value function factorisation for deep multiagent reinforcement learning","volume":"21","author":"Rashid","year":"2020","journal-title":"J. Mach. Learn. Res"},{"key":"ref23","volume-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"key":"ref24","article-title":"Deep reinforcement learning in parameterized action space","author":"Hausknecht","year":"2015","journal-title":"arXiv preprint arXiv:1511.04143"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3189021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"}],"event":{"name":"2024 International Conference on Advanced Robotics and Mechatronics (ICARM)","location":"Tokyo, Japan","start":{"date-parts":[[2024,7,8]]},"end":{"date-parts":[[2024,7,10]]}},"container-title":["2024 International Conference on Advanced Robotics and Mechatronics (ICARM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10715684\/10715739\/10715990.pdf?arnumber=10715990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T04:50:00Z","timestamp":1729313400000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10715990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,8]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icarm62033.2024.10715990","relation":{},"subject":[],"published":{"date-parts":[[2024,7,8]]}}}