{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T23:14:19Z","timestamp":1740179659934,"version":"3.37.3"},"reference-count":45,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"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":["61836011","62021001"],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MCC Lab of Information Science and Technology Institution, USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Games"],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tg.2022.3232390","type":"journal-article","created":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T18:28:32Z","timestamp":1672165712000},"page":"140-150","source":"Crossref","is-referenced-by-count":9,"title":["CTDS: Centralized Teacher With Decentralized Student for Multiagent Reinforcement Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4895-990X","authenticated-orcid":false,"given":"Jian","family":"Zhao","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"given":"Xunhan","family":"Hu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6077-6711","authenticated-orcid":false,"given":"Mingyu","family":"Yang","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6610-721X","authenticated-orcid":false,"given":"Jiangcheng","family":"Zhu","sequence":"additional","affiliation":[{"name":"Huawei Cloud, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v25i1.7886"},{"article-title":"Guided deep reinforcement learning for swarm systems","year":"2017","author":"Httenrauch","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2007.913919"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3095264"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3065410"},{"article-title":"Value-decomposition networks for cooperative multi-agent learning","year":"2017","author":"Sunehag","key":"ref7"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09421-1"},{"article-title":"Dota 2 with large scale deep reinforcement learning","year":"2019","author":"Openai","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6144"},{"key":"ref11","first-page":"2137","article-title":"Learning to communicate with deep multi-agent reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"29","author":"Foerster","year":"2016"},{"key":"ref12","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rashid","year":"2018"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2447"},{"key":"ref15","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume":"30","author":"Lowe","year":"2017","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref17","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Son","year":"2019"},{"article-title":"QATTEN: A general framework for cooperative multiagent reinforcement learning","year":"2020","author":"Yang","key":"ref18"},{"key":"ref19","first-page":"2021","article-title":"QPLEX: Duplex dueling multi-agent Q-learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"author":"Samvelyan","key":"ref20","article-title":"The StarCraft multi-agent challenge"},{"key":"ref21","first-page":"1","article-title":"A review of cooperative multi-agent deep reinforcement learning","volume-title":"Appl. Intell.","author":"OroojlooyJadid","year":"2022"},{"issue":"1","key":"ref22","first-page":"8618","article-title":"Structured cooperative reinforcement learning with time-varying composite action space","volume":"44","author":"Li","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref23","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Sukhbaatar","year":"2016"},{"article-title":"Multiagent bidirectionally-coordinated nets: Emergence of human-level coordination in learning to play StarCraft combat games","year":"2017","author":"Peng","key":"ref24"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23860\/diss-li-hepfeng-2023"},{"article-title":"Multi-agent reinforcement learning is a sequence modeling problem","year":"2022","author":"Wen","key":"ref26"},{"key":"ref27","first-page":"330","article-title":"Multi-agent reinforcement learning: Independent versus cooperative agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan","year":"1993"},{"article-title":"Is independent learning all you need in the StarCraft multi-agent challenge?","year":"2020","author":"de Witt","key":"ref28"},{"article-title":"The surprising effectiveness of PPO in cooperative, multi-agent games","year":"2021","author":"Yu","key":"ref29"},{"key":"ref30","article-title":"DOP: Off-policy multi-agent decomposed policy gradients","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang","year":"2020"},{"key":"ref31","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Rashid","year":"2020"},{"key":"ref32","first-page":"7613","article-title":"MAVEN: Multi-agent variational exploration","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"32","author":"Mahajan","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929038"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2942592"},{"article-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref35"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1139"},{"key":"ref37","first-page":"5142","article-title":"Towards understanding knowledge distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Phuong","year":"2019"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref39","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TG.2021.3113644"},{"key":"ref42","article-title":"Policy distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Rusu","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8"},{"article-title":"MA-gym: Collection of multi-agent environments based on OpenAI gym","year":"2019","author":"Koul","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5878"}],"container-title":["IEEE Transactions on Games"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7782673\/10474491\/09999468.pdf?arnumber=9999468","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,6]],"date-time":"2024-09-06T08:53:55Z","timestamp":1725612835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9999468\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":45,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tg.2022.3232390","relation":{},"ISSN":["2475-1502","2475-1510"],"issn-type":[{"type":"print","value":"2475-1502"},{"type":"electronic","value":"2475-1510"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}