{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T07:40:11Z","timestamp":1737445211010,"version":"3.33.0"},"reference-count":18,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,6]],"date-time":"2024-10-06T00:00:00Z","timestamp":1728172800000},"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":["U23B2060,62173294"],"award-info":[{"award-number":["U23B2060,62173294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Provincial Natural Science Foundation","doi-asserted-by":"publisher","award":["LZ24F030001"],"award-info":[{"award-number":["LZ24F030001"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,10,6]]},"DOI":"10.1109\/smc54092.2024.10831538","type":"proceedings-article","created":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:39:20Z","timestamp":1737398360000},"page":"5087-5092","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Policy Optimization for Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Shunfan","family":"He","sequence":"first","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronghao","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Senlin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Electrical Engineering, Zhejiang University,Hangzhou,China,310027"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meiqin","family":"Liu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University,National Key Laboratory of Human-Machine Hybrid Augmented Intelligence,Xi'an,China,710049"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref2","article-title":"Continuous control with deep reinforcement learning","volume-title":"4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings","author":"Lillicrap","year":"2016"},{"key":"ref3","article-title":"QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsmdssan, Stockholm, Sweden, July 10-15, 2018","author":"Rashid","year":"2018"},{"key":"ref4","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Lowe","year":"2017"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2021.3078100"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2241057"},{"key":"ref8","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4 ssan, Stockholm, Sweden, July 10-15, 2018","author":"Zhang","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683356"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICTAI50040.2020.00011"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4419-8853-9","volume-title":"Introductory Lectures on Convex Optimization - A Basic Course","volume":"87","author":"Nesterov","year":"2004"},{"key":"ref12","article-title":"Global convergence of policy gradient methods for the linear quadratic regulator","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018","author":"Fazel","year":"2018"},{"key":"ref13","article-title":"Derivative-free methods for policy optimization: Guarantees for linear quadratic systems","author":"Malik","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2021.3128592"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/ACC53348.2022.9867152"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.automatica.2021.110006"},{"volume-title":"Cooperative multi-agent reinforcement learning with partial observations","year":"2020","author":"Zhang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"}],"event":{"name":"2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","start":{"date-parts":[[2024,10,6]]},"location":"Kuching, Malaysia","end":{"date-parts":[[2024,10,10]]}},"container-title":["2024 IEEE International Conference on Systems, Man, and Cybernetics (SMC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10830919\/10830920\/10831538.pdf?arnumber=10831538","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:59:14Z","timestamp":1737442754000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10831538\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,6]]},"references-count":18,"URL":"https:\/\/doi.org\/10.1109\/smc54092.2024.10831538","relation":{},"subject":[],"published":{"date-parts":[[2024,10,6]]}}}