{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:41:13Z","timestamp":1740102073078,"version":"3.37.3"},"reference-count":30,"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":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076238,62222606"],"award-info":[{"award-number":["62076238,62222606"]}],"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\/ijcnn54540.2023.10191504","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":0,"title":["TLMIX: Twin Leader Mixing Network for Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yu","family":"Zhang","sequence":"first","affiliation":[{"name":"Qinghai University,Department of Computer Technology and Applications,Xining,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Independent Researcher"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusheng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Qinghai University,Department of Computer Technology and Applications,Xining,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University,Department of Computer Science and Technology,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pin","family":"Tao","sequence":"additional","affiliation":[{"name":"Qinghai University,Department of Computer Technology and Applications,Xining,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"10199","article-title":"Weighted QMIX: Expanding monotonic value function factorisation for deep multi-agent reinforcement learning","author":"rashid","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"QTRAN++: Improved value transformation for cooper-ative multi-agent reinforcement learning","author":"son","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref15","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"fujimoto","year":"0","journal-title":"In International Conference on Machine Learning"},{"key":"ref14","first-page":"12208","article-title":"FACMAC: Factored multi-agent centralised policy gradients","author":"peng","year":"2021","journal-title":"Ad-vances in Neural Information Processing Systems"},{"key":"ref30","first-page":"29","article-title":"Deep recurrent q-learning for partially observable MDPs","author":"hausknecht","year":"2015","journal-title":"AAAI Fall Symposium on Sequential Decision Making for Intelligent Agents (SDMIA)"},{"key":"ref11","first-page":"5887","article-title":"QTRAN: Learning to factorize with transformation for cooperative multi -agent reinforcement learning","author":"son","year":"2019","journal-title":"Ternational Conference on Machine Learning"},{"key":"ref10","first-page":"4295","article-title":"QMIX: Monotonic value function factorisation for deep multi -agent reinforce-ment learning","author":"rashid","year":"2018","journal-title":"International Conference on Machine Learning"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2012.2219061"},{"key":"ref1","doi-asserted-by":"crossref","first-page":"6672","DOI":"10.1609\/aaai.v34i04.6144","article-title":"Mastering complex con-trol in moba games with deep reinforcement learning","author":"ye","year":"2020","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref17","first-page":"980","article-title":"Deep coordi-nation graphs","author":"boehmer","year":"2020","journal-title":"International Conference on Machine Learning"},{"key":"ref16","first-page":"2186","article-title":"StarCraft multi-agent challenge","author":"samvelyan","year":"2019","journal-title":"International Conference on Autonomous Agents and Multiagent Systems"},{"key":"ref19","first-page":"2974","article-title":"Counterfactual multi-agent policy gra-dients","author":"foerster","year":"2018","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"ref18","article-title":"Rethinking the implementation tricks and monotonic-ity constraint in cooperative multi -agent reinforcement learning","author":"hu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref24","first-page":"26437","article-title":"Coordinated proximal policy optimization","author":"wu","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref23","article-title":"Is indepen-dent learning all you need in the StarCraft multi -agent challenge?","author":"de witt","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref26","article-title":"Rethinking individual global max in cooperative multi -agent reinforcement learning","author":"hong","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref25","first-page":"1","article-title":"RODE: Learning roles to decompose multi-agent tasks","author":"wang","year":"2021","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/181"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0172395"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/420"},{"key":"ref28","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ar Xiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-28929-8","author":"oliehoek","year":"2016","journal-title":"A Concise Introduction to Decentralized POMDPs"},{"key":"ref8","article-title":"Surprising effectiveness of ppo in cooperative, multi-agent games","author":"yu","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref7","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref9","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi -agent learning based on team reward","author":"sunehag","year":"2018","journal-title":"Inernational Conference on Autonomous Agents and Multiagent Systerm"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.01.031"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2005.04.039"},{"key":"ref6","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"International Conference on Machine Learning"},{"key":"ref5","article-title":"Continuous con-trol with deep reinforcement learning","author":"lillicrap","year":"0","journal-title":"International Conference on Learning Representations"}],"event":{"name":"2023 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2023,6,18]]},"location":"Gold Coast, Australia","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\/10191504.pdf?arnumber=10191504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T17:42:21Z","timestamp":1692639741000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10191504\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,18]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/ijcnn54540.2023.10191504","relation":{},"subject":[],"published":{"date-parts":[[2023,6,18]]}}}