{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:27:53Z","timestamp":1774538873948,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2110259"],"award-info":[{"award-number":["CNS-2110259"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-2112471"],"award-info":[{"award-number":["CNS-2112471"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2324052"],"award-info":[{"award-number":["IIS-2324052"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["D24AP00265"],"award-info":[{"award-number":["D24AP00265"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["HR0011-25-2-0019"],"award-info":[{"award-number":["HR0011-25-2-0019"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-24-1-2729"],"award-info":[{"award-number":["N00014-24-1-2729"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3704413.3764464","type":"proceedings-article","created":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:08:23Z","timestamp":1761239303000},"page":"241-250","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Consensus-based Decentralized Multi-agent Reinforcement Learning for Random Access Network Optimization"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1996-3128","authenticated-orcid":false,"given":"Myeung Suk","family":"Oh","sequence":"first","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6750-652X","authenticated-orcid":false,"given":"Zhiyao","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7457-9893","authenticated-orcid":false,"given":"FNU","family":"Hairi","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Whitewater, Whitewater, Wisconsin, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6757-105X","authenticated-orcid":false,"given":"Alvaro","family":"Velasquez","sequence":"additional","affiliation":[{"name":"University of Colorado Boulder, Boulder, Colorado, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8844-3233","authenticated-orcid":false,"given":"Jia","family":"Liu","sequence":"additional","affiliation":[{"name":"The Ohio State University, Columbus, Ohio, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.21236\/AD0707853"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3041765"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3430368"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2005.862098"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/1499949.1499985"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2006.874516"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2001146"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2016.2593666"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of International Conference on Machine Learning (ICML). PMLR, 3794\u20133834","author":"Chen Ziyi","year":"2022","unstructured":"Ziyi Chen, Yi Zhou, Rong-Rong Chen, and Shaofeng Zou. 2022. Sample and communication-efficient decentralized actor-critic algorithms with finite-time analysis. In Proceedings of International Conference on Machine Learning (ICML). PMLR, 3794\u20133834."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095828"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2012.128"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3063822"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2012.2215964"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3143251"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of International Conference on Autonomous Agents and Multiagent Systems (AAMAS). 789\u2013797","author":"Zhang Zifan","year":"2024","unstructured":"Hairi, Zifan Zhang, and Jia Liu. 2024. Sample and communication efficient fully decentralized MARL policy evaluation via a new approach: Local TD update. In Proceedings of International Conference on Autonomous Agents and Multiagent Systems (AAMAS). 789\u2013797."},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of International Conference on Learning Representations (ICLR). PMLR.","author":"Hairi FNU","year":"2022","unstructured":"FNU Hairi, Jia Liu, and Songtao Lu. 2022. Finite-time convergence and sample complexity of multi-Agent actor-critic reinforcement learning with average reward. In Proceedings of International Conference on Learning Representations (ICLR). PMLR."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2994525"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC57260.2024.10571310"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2012.2204032"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2010.2081490"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2009.2035046"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1975.1092768"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10030318"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3506972"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2010.89"},{"key":"e_1_3_2_1_26_1","volume-title":"Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971","author":"Lillicrap Timothy P","year":"2015","unstructured":"Timothy P Lillicrap, Jonathan J Hunt, Alexander Pritzel, Nicolas Heess, Tom Erez, Yuval Tassa, David Silver, and Daan Wierstra. 2015. Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13638-021-02010-5"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","first-page":"825","DOI":"10.1109\/TNET.2011.2177101","article-title":"Q-CSMA: Queue-length-based CSMA\/CA algorithms for achieving maximum throughput and low delay in wireless networks","volume":"20","author":"Ni Jian","year":"2011","unstructured":"Jian Ni, Bo Tan, and Rayadurgam Srikant. 2011. Q-CSMA: Queue-length-based CSMA\/CA algorithms for achieving maximum throughput and low delay in wireless networks. IEEE\/ACM Transactions on Networking 20, 3 (2011), 825\u2013836.","journal-title":"IEEE\/ACM Transactions on Networking"},{"key":"e_1_3_2_1_29_1","unstructured":"Myeung Suk Oh Zhiyao Zhang Hairi Alvaro Velasquez and Jia Liu. [n. d.]. Technical report on consensus-based decentralized multi-agent reinforcement learning for random access network optimization. https:\/\/kevinliu-osu.github.io\/publications\/DecMARL_RA_TR.pdf"},{"key":"e_1_3_2_1_30_1","first-page":"7","article-title":"Wireless communication technologies for smart grid distribution networks","volume":"47","author":"Rodriguez Juan Carlos","year":"2023","unstructured":"Juan Carlos Rodriguez, Felipe Grijalva, Marcelo Garc\u00eda, Diana Estefan\u00eda Ch\u00e9rrez Barrag\u00e1n, Byron Alejandro Acu\u00f1a Acurio, and Henry Carvajal. 2023. Wireless communication technologies for smart grid distribution networks. Engineering Proceedings 47, 1 (2023), 7.","journal-title":"Engineering Proceedings"},{"key":"e_1_3_2_1_31_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of Conference on Learning Theory. PMLR, 2803\u20132830","author":"Srikant Rayadurgam","year":"2019","unstructured":"Rayadurgam Srikant and Lei Ying. 2019. Finite-time error bounds for linear stochastic approximation and TD learning. In Proceedings of Conference on Learning Theory. PMLR, 2803\u20132830."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Richard S Sutton Andrew G Barto et al. 1998. Reinforcement learning: An introduction. MIT press Cambridge.","DOI":"10.1109\/TNN.1998.712192"},{"key":"e_1_3_2_1_34_1","volume-title":"Collective dynamics of 'small-world' networks. Nature 393, 6684","author":"Watts Duncan J","year":"1998","unstructured":"Duncan J Watts and Steven H Strogatz. 1998. Collective dynamics of 'small-world' networks. Nature 393, 6684 (1998), 440\u2013442."},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS). 4358\u20134369","author":"Xu Tengyu","year":"2020","unstructured":"Tengyu Xu, Zhe Wang, and Yingbin Liang. 2020. Improving sample complexity bounds for (natural) actor-critic algorithms. In Proceedings of Advances in Neural Information Processing Systems (NeurIPS). 4358\u20134369."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3277836"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3057826"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904329"},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of International Conference on Machine Learning (ICML). PMLR, 5872\u20135881","author":"Zhang Kaiqing","year":"2018","unstructured":"Kaiqing Zhang, Zhuoran Yang, Han Liu, Tong Zhang, and Tamer Basar. 2018. Fully decentralized multi-agent reinforcement learning with networked agents. In Proceedings of International Conference on Machine Learning (ICML). PMLR, 5872\u20135881."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2020-Fall49728.2020.9348485"}],"event":{"name":"MobiHoc '25: Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","location":"Rice University Houston TX USA","acronym":"MobiHoc '25","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704413.3764464","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3704413.3764464","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:09:06Z","timestamp":1761239346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3704413.3764464"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,23]]},"references-count":40,"alternative-id":["10.1145\/3704413.3764464","10.1145\/3704413"],"URL":"https:\/\/doi.org\/10.1145\/3704413.3764464","relation":{},"subject":[],"published":{"date-parts":[[2025,10,23]]},"assertion":[{"value":"2025-10-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}