{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T12:40:59Z","timestamp":1759840859163,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","funder":[{"name":"German Federal Ministry of Education and Research","award":["16KISK092"],"award-info":[{"award-number":["16KISK092"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,14]]},"DOI":"10.1145\/3712255.3734328","type":"proceedings-article","created":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T15:15:44Z","timestamp":1754925344000},"page":"2143-2151","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Self-organized Swarm Reinforcement Learning under Spontaneous Communications"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2968-3306","authenticated-orcid":false,"given":"Qihao","family":"Shan","sequence":"first","affiliation":[{"name":"Chair of Computational Intelligence, Faculty of Computer Science, Otto-von-Guericke University, Magdeburg, Saxony-Anhalt, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9917-5227","authenticated-orcid":false,"given":"Sanaz","family":"Mostaghim","sequence":"additional","affiliation":[{"name":"Chair of Computational Intelligence, Faculty of Computer Science, Otto-von-Guericke University, Magdeburg, Saxony-Anhalt, Germany"}]}],"member":"320","published-online":{"date-parts":[[2025,8,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Finite-time analysis of the multiarmed bandit problem. Machine learning 47","author":"Auer Peter","year":"2002","unstructured":"Peter Auer, Nicolo Cesa-Bianchi, and Paul Fischer. 2002. Finite-time analysis of the multiarmed bandit problem. Machine learning 47 (2002), 235\u2013256."},{"key":"e_1_3_2_1_2_1","volume-title":"Collective decision-making. Current opinion in behavioral sciences 16","author":"Bose Thomas","year":"2017","unstructured":"Thomas Bose, Andreagiovanni Reina, and James AR Marshall. 2017. Collective decision-making. Current opinion in behavioral sciences 16 (2017), 30\u201334."},{"key":"e_1_3_2_1_3_1","first-page":"1","article-title":"A survey on multi-player bandits","volume":"25","author":"Boursier Etienne","year":"2024","unstructured":"Etienne Boursier and Vianney Perchet. 2024. A survey on multi-player bandits. Journal of Machine Learning Research 25, 137 (2024), 1\u201345.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-012-0075-2"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2018.00012"},{"volume-title":"Self-organization in biological systems","author":"Camazine Scott","key":"e_1_3_2_1_6_1","unstructured":"Scott Camazine, Jean-Louis Deneubourg, Guy Theraula, James Sneyd, and Nigel R Franks. 2020. Self-organization in biological systems. Princeton university press."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.3390\/app11114948"},{"key":"e_1_3_2_1_8_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 3903\u20133930","author":"Janice Chen Yu-Zhen","year":"2023","unstructured":"Yu-Zhen Janice Chen, Lin Yang, Xuchuang Wang, Xutong Liu, Mohammad Hajiesmaili, John CS Lui, and Don Towsley. 2023. On-demand communication for asynchronous multi-agent bandits. In International Conference on Artificial Intelligence and Statistics. PMLR, 3903\u20133930."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.9746\/jcmsi.10.495"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3072740"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2017.0928"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.5555\/1622737.1622748"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1287\/moor.12.2.262"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/4235.728210"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-011-0062-z"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3074122"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.109.054307"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366701"},{"key":"e_1_3_2_1_19_1","volume-title":"Dynamics of majority rule with differential latencies. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics 83, 3","author":"Scheidler Alexander","year":"2011","unstructured":"Alexander Scheidler. 2011. Dynamics of majority rule with differential latencies. Physical Review E\u2014Statistical, Nonlinear, and Soft Matter Physics 83, 3 (2011), 031116."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952664"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI50451.2021.9659868"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11721-022-00214-z"},{"key":"e_1_3_2_1_23_1","volume-title":"International conference on artificial intelligence and statistics. PMLR, 2917\u20132925","author":"Shi Chengshuai","year":"2021","unstructured":"Chengshuai Shi, Cong Shen, and Jing Yang. 2021. Federated multi-armed bandits with personalization. In International conference on artificial intelligence and statistics. PMLR, 2917\u20132925."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Aleksandrs Slivkins et al. 2019. Introduction to multi-armed bandits. Foundations and Trends\u00ae in Machine Learning 12 1\u20132 (2019) 1\u2013286.","DOI":"10.1561\/2200000068"},{"key":"e_1_3_2_1_25_1","unstructured":"Richard S Sutton Andrew G Barto et al. 1998. Reinforcement learning: An introduction. Vol. 1. MIT press Cambridge."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. 1305\u20131314","author":"Valentini Gabriele","year":"2015","unstructured":"Gabriele Valentini, Heiko Hamann, and Marco Dorigo. 2015. Efficient Decision-Making in a Self-Organizing Robot Swarm: On the Speed Versus Accuracy Trade-Off. In Proceedings of the 2015 International Conference on Autonomous Agents and Multiagent Systems. 1305\u20131314."},{"key":"e_1_3_2_1_27_1","volume-title":"AAMAS","volume":"14","author":"Valentini Gabriele","year":"2014","unstructured":"Gabriele Valentini, Heiko Hamann, Marco Dorigo, et al. 2014. Self-organized collective decision making: The weighted voter model. In AAMAS, Vol. 14. Citeseer, 45\u201352."},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 4120\u20134129","author":"Wang Po-An","year":"2020","unstructured":"Po-An Wang, Alexandre Proutiere, Kaito Ariu, Yassir Jedra, and Alessio Russo. 2020. Optimal algorithms for multiplayer multi-armed bandits. In International Conference on Artificial Intelligence and Statistics. PMLR, 4120\u20134129."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796901"},{"key":"e_1_3_2_1_30_1","first-page":"8885","article-title":"Cooperative stochastic bandits with asynchronous agents and constrained feedback","volume":"34","author":"Yang Lin","year":"2021","unstructured":"Lin Yang, Yu-Zhen Janice Chen, Stephen Pasteris, Mohammad Hajiesmaili, John Lui, and Don Towsley. 2021. Cooperative stochastic bandits with asynchronous agents and constrained feedback. Advances in Neural Information Processing Systems 34 (2021), 8885\u20138897.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","volume-title":"Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control","author":"Zhang Kaiqing","year":"2021","unstructured":"Kaiqing Zhang, Zhuoran Yang, and Tamer Ba\u015far. 2021. Multi-agent reinforcement learning: A selective overview of theories and algorithms. Handbook of reinforcement learning and control (2021), 321\u2013384."}],"event":{"name":"GECCO '25 Companion: Genetic and Evolutionary Computation Conference Companion","sponsor":["SIGEVO ACM Special Interest Group on Genetic and Evolutionary Computation"],"location":"NH Malaga Hotel Malaga Spain","acronym":"GECCO '25 Companion"},"container-title":["Proceedings of the Genetic and Evolutionary Computation Conference Companion"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3712255.3734328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T12:00:36Z","timestamp":1759838436000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3712255.3734328"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,14]]},"references-count":31,"alternative-id":["10.1145\/3712255.3734328","10.1145\/3712255"],"URL":"https:\/\/doi.org\/10.1145\/3712255.3734328","relation":{},"subject":[],"published":{"date-parts":[[2025,7,14]]},"assertion":[{"value":"2025-08-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}