{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,27]],"date-time":"2026-02-27T03:48:26Z","timestamp":1772164106146,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":12,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T00:00:00Z","timestamp":1687132800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Amazon AWS"},{"name":"PIMCO Postdoc Fellowship"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2154171, 2146814, 2136197, 2106403, 2105648"],"award-info":[{"award-number":["2154171, 2146814, 2136197, 2106403, 2105648"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"C3 AI Institute"},{"name":"Simoudis Discovery Prize"},{"name":"PIMCO Graduate Fellowship"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,6,19]]},"DOI":"10.1145\/3578338.3593545","type":"proceedings-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T23:02:49Z","timestamp":1686697369000},"page":"83-84","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Global Convergence of Localized Policy Iteration in Networked Multi-Agent Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5677-4748","authenticated-orcid":false,"given":"Yizhou","family":"Zhang","sequence":"first","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5466-3550","authenticated-orcid":false,"given":"Guannan","family":"Qu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2559-8622","authenticated-orcid":false,"given":"Pan","family":"Xu","sequence":"additional","affiliation":[{"name":"Duke University, Durham, NC, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6524-2877","authenticated-orcid":false,"given":"Yiheng","family":"Lin","sequence":"additional","affiliation":[{"name":"California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9915-5595","authenticated-orcid":false,"given":"Zaiwei","family":"Chen","sequence":"additional","affiliation":[{"name":"California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5923-0199","authenticated-orcid":false,"given":"Adam","family":"Wierman","sequence":"additional","affiliation":[{"name":"California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,6,19]]},"reference":[{"key":"e_1_3_2_3_1_1","volume-title":"Reinforcement learning for selective key applications in power systems: Recent advances and future challenges","author":"Chen Xin","year":"2022","unstructured":"Xin Chen, Guannan Qu, Yujie Tang, Steven Low, and Na Li. 2022. Reinforcement learning for selective key applications in power systems: Recent advances and future challenges. IEEE Transactions on Smart Grid (2022)."},{"key":"e_1_3_2_3_2_1","first-page":"746","article-title":"The dynamics of reinforcement learning in cooperative multiagent systems","volume":"1998","author":"Claus Caroline","year":"1998","unstructured":"Caroline Claus and Craig Boutilier. 1998. The dynamics of reinforcement learning in cooperative multiagent systems. AAAI\/IAAI, Vol. 1998 (1998), 746--752.","journal-title":"AAAI\/IAAI"},{"key":"e_1_3_2_3_3_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622434.1622447"},{"key":"e_1_3_2_3_4_1","first-page":"7825","article-title":"Multi-agent reinforcement learning in stochastic networked systems","volume":"34","author":"Lin Yiheng","year":"2021","unstructured":"Yiheng Lin, Guannan Qu, Longbo Huang, and Adam Wierman. 2021. Multi-agent reinforcement learning in stochastic networked systems. Advances in Neural Information Processing Systems, Vol. 34 (2021), 7825--7837.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_3_5_1","volume-title":"Nature","volume":"518","author":"Mnih Volodymyr","year":"2015","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al. 2015. Human-level control through deep reinforcement learning. Nature, Vol. 518, 7540 (2015), 529."},{"key":"e_1_3_2_3_6_1","first-page":"2074","article-title":"Scalable multi-agent reinforcement learning for networked systems with average reward","volume":"33","author":"Qu Guannan","year":"2020","unstructured":"Guannan Qu, Yiheng Lin, Adam Wierman, and Na Li. 2020a. Scalable multi-agent reinforcement learning for networked systems with average reward. Advances in Neural Information Processing Systems, Vol. 33 (2020), 2074--2086.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_3_7_1","unstructured":"Guannan Qu Adam Wierman and Na Li. 2020b. Scalable reinforcement learning of localized policies for multi-agent networked systems. In Learning for Dynamics and Control. PMLR 256--266."},{"key":"e_1_3_2_3_8_1","volume-title":"Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al.","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J Maddison, Arthur Guez, Laurent Sifre, George Van Den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Veda Panneershelvam, Marc Lanctot, et al. 2016. Mastering the game of Go with deep neural networks and tree search. nature, Vol. 529, 7587 (2016), 484."},{"key":"e_1_3_2_3_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/3091529.3091572"},{"key":"e_1_3_2_3_10_1","doi-asserted-by":"crossref","unstructured":"Neil Walton and Kuang Xu. 2021. Learning and information in stochastic networks and queues. In Tutorials in Operations Research: Emerging Optimization Methods and Modeling Techniques with Applications. INFORMS 161--198.","DOI":"10.1287\/educ.2021.0235"},{"key":"e_1_3_2_3_11_1","volume-title":"International conference on machine learning. PMLR, 5571--5580","author":"Yang Yaodong","year":"2018","unstructured":"Yaodong Yang, Rui Luo, Minne Li, Ming Zhou, Weinan Zhang, and Jun Wang. 2018. Mean field multi-agent reinforcement learning. In International conference on machine learning. PMLR, 5571--5580."},{"key":"e_1_3_2_3_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3610072"}],"event":{"name":"SIGMETRICS '23: ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems","location":"Orlando Florida United States","acronym":"SIGMETRICS '23","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation"]},"container-title":["Abstract Proceedings of the 2023 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578338.3593545","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578338.3593545","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3578338.3593545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T12:47:05Z","timestamp":1750164425000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3578338.3593545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,19]]},"references-count":12,"alternative-id":["10.1145\/3578338.3593545","10.1145\/3578338"],"URL":"https:\/\/doi.org\/10.1145\/3578338.3593545","relation":{"is-identical-to":[{"id-type":"doi","id":"10.1145\/3606376.3593545","asserted-by":"object"}]},"subject":[],"published":{"date-parts":[[2023,6,19]]},"assertion":[{"value":"2023-06-19","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}