{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T10:37:40Z","timestamp":1778495860990,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":38,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,11,30]],"date-time":"2023-11-30T00:00:00Z","timestamp":1701302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,30]]},"DOI":"10.1145\/3627676.3627678","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T06:05:14Z","timestamp":1703916314000},"page":"1-9","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Learning to Coordinate with Anyone"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7595-3104","authenticated-orcid":false,"given":"Lei","family":"Yuan","sequence":"first","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7017-6488","authenticated-orcid":false,"given":"Lihe","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0570-4969","authenticated-orcid":false,"given":"Ziqian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8164-3410","authenticated-orcid":false,"given":"Feng","family":"Chen","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6156-4903","authenticated-orcid":false,"given":"Tianyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9618-6556","authenticated-orcid":false,"given":"Cong","family":"Guan","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8011-3430","authenticated-orcid":false,"given":"Yang","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3378-3630","authenticated-orcid":false,"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[{"name":"Nanjing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Rujikorn Charakorn Poramate Manoonpong and Nat Dilokthanakul. 2023. Generating Diverse Cooperative Agents by Learning Incompatible Policies. In ICLR."},{"key":"e_1_3_2_2_2_1","unstructured":"Kenneth Derek and Phillip Isola. 2021. Adaptable agent populations via a generative model of policies. In NeurIPS. 3902\u20133913."},{"key":"e_1_3_2_2_3_1","unstructured":"Hao Ding Chengxing Jia Cong Guan Feng Chen Lei Yuan Zongzhang Zhang and Yang Yu. 2023. Coordination Scheme Probing for Generalizable Multi-Agent Reinforcement Learning. https:\/\/openreview.net\/forum?id=PAKkOriJBd"},{"key":"e_1_3_2_2_4_1","volume-title":"Few-shot teamwork. preprint arXiv:2207.09300","author":"Fosong Elliot","year":"2022","unstructured":"Elliot Fosong, Arrasy Rahman, Ignacio Carlucho, and Stefano\u00a0V Albrecht. 2022. Few-shot teamwork. preprint arXiv:2207.09300 (2022)."},{"key":"e_1_3_2_2_5_1","unstructured":"Bent Fuglede and Flemming Tops\u00f8e. 2004. Jensen-Shannon divergence and Hilbert space embedding. In ISIT."},{"key":"e_1_3_2_2_6_1","unstructured":"Johannes Heinrich Marc Lanctot and David Silver. 2015. Fictitious self-play in extensive-form games. In ICML. 805\u2013813."},{"key":"e_1_3_2_2_7_1","volume-title":"Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364, 6443","author":"Jaderberg Max","year":"2019","unstructured":"Max Jaderberg, Wojciech\u00a0M Czarnecki, Iain Dunning, Luke Marris, Guy Lever, Antonio\u00a0Garcia Castaneda, Charles Beattie, Neil\u00a0C Rabinowitz, Ari\u00a0S Morcos, Avraham Ruderman, 2019. Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science 364, 6443 (2019), 859\u2013865."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"e_1_3_2_2_9_1","volume-title":"Summary of chatgpt\/gpt-4 research and perspective towards the future of large language models. preprint arXiv:2304.01852","author":"Liu Yiheng","year":"2023","unstructured":"Yiheng Liu, Tianle Han, Siyuan Ma, Jiayue Zhang, Yuanyuan Yang, Jiaming Tian, Hao He, Antong Li, Mengshen He, Zhengliang Liu, 2023. Summary of chatgpt\/gpt-4 research and perspective towards the future of large language models. preprint arXiv:2304.01852 (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"Jean Harb\u00a0Pieter Abbeel, and Igor Mordatch","author":"Lowe Ryan","year":"2017","unstructured":"Ryan Lowe, Yi Wu, Aviv Tamar, Jean Harb\u00a0Pieter Abbeel, and Igor Mordatch. 2017. Multi-agent actor-critic for mixed cooperative-competitive environments. In NIPS. 6379\u20136390."},{"key":"e_1_3_2_2_11_1","unstructured":"Andrei Lupu Brandon Cui Hengyuan Hu and Jakob Foerster. 2021. Trajectory diversity for zero-shot coordination. In ICML. 7204\u20137213."},{"key":"e_1_3_2_2_12_1","volume-title":"On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics","author":"Mann B","year":"1947","unstructured":"Henry\u00a0B Mann and Donald\u00a0R Whitney. 1947. On a test of whether one of two random variables is stochastically larger than the other. The annals of mathematical statistics (1947), 50\u201360."},{"key":"e_1_3_2_2_13_1","volume-title":"A Survey of Ad Hoc Teamwork: Definitions, Methods, and Open Problems. preprint arXiv:2202.10450","author":"Mirsky Reuth","year":"2022","unstructured":"Reuth Mirsky, Ignacio Carlucho, Arrasy Rahman, Elliot Fosong, William Macke, Mohan Sridharan, Peter Stone, and Stefano\u00a0V Albrecht. 2022. A Survey of Ad Hoc Teamwork: Definitions, Methods, and Open Problems. preprint arXiv:2202.10450 (2022)."},{"key":"e_1_3_2_2_14_1","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"Oliehoek A","unstructured":"Frans\u00a0A Oliehoek and Christopher Amato. 2016. A Concise Introduction to Decentralized POMDPs. Springer."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04105-y"},{"key":"e_1_3_2_2_16_1","unstructured":"Georgios Papoudakis Filippos Christianos and Stefano Albrecht. 2021. Agent modelling under partial observability for deep reinforcement learning. In NeurIPS. 19210\u201319222."},{"key":"e_1_3_2_2_17_1","unstructured":"Georgios Papoudakis Filippos Christianos Lukas Sch\u00e4fer and Stefano\u00a0V Albrecht. 2021. Benchmarking multi-agent deep reinforcement learning algorithms in cooperative tasks. In NeurIPS."},{"key":"e_1_3_2_2_18_1","volume-title":"QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning. In ICML. 4295\u20134304.","author":"Rashid Tabish","year":"2018","unstructured":"Tabish Rashid, Mikayel Samvelyan, Christian Schroeder, Gregory Farquhar, Jakob Foerster, and Shimon Whiteson. 2018. QMIX: Monotonic value function factorisation for deep multi-agent reinforcement learning. In ICML. 4295\u20134304."},{"key":"e_1_3_2_2_19_1","unstructured":"David Rolnick Arun Ahuja Jonathan Schwarz Timothy\u00a0P. Lillicrap and Greg Wayne. 2018. Experience Replay for Continual Learning. In NeurIPS. 348\u2013358."},{"key":"e_1_3_2_2_20_1","unstructured":"Mikayel Samvelyan Tabish Rashid Christian\u00a0Schr\u00f6der de Witt Gregory Farquhar Nantas Nardelli Tim G.\u00a0J. Rudner Chia-Man Hung Philip H.\u00a0S. Torr Jakob\u00a0N. Foerster and Shimon Whiteson. 2019. The StarCraft Multi-Agent Challenge. In AAMAS. 2186\u20132188."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2903261"},{"key":"e_1_3_2_2_22_1","volume-title":"A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 6419","author":"Silver David","year":"2018","unstructured":"David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, 2018. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science 362, 6419 (2018), 1140\u20131144."},{"key":"e_1_3_2_2_23_1","unstructured":"DJ Strouse Kevin McKee Matt Botvinick Edward Hughes and Richard Everett. 2021. Collaborating with humans without human data. In NeurIPS. 14502\u201314515."},{"key":"e_1_3_2_2_24_1","unstructured":"Peter Sunehag Guy Lever Audrunas Gruslys Wojciech\u00a0Marian Czarnecki Vinicius Zambaldi Max Jaderberg Marc Lanctot Nicolas Sonnerat Joel\u00a0Z Leibo Karl Tuyls 2018. Value-decomposition networks for cooperative multi-agent learning based on team reward. In AAMAS. 2085\u20132087."},{"key":"e_1_3_2_2_25_1","volume-title":"a self-teaching backgammon program, achieves master-level play. Neural computation 6, 2","author":"Tesauro Gerald","year":"1994","unstructured":"Gerald Tesauro. 1994. TD-Gammon, a self-teaching backgammon program, achieves master-level play. Neural computation 6, 2 (1994), 215\u2013219."},{"key":"e_1_3_2_2_26_1","unstructured":"Johannes Treutlein Michael Dennis Caspar Oesterheld and Jakob Foerster. 2021. A new formalism method and open issues for zero-shot coordination. In ICML. 10413\u201310423."},{"key":"e_1_3_2_2_27_1","unstructured":"Jianhong Wang Wangkun Xu Yunjie Gu Wenbin Song and Tim\u00a0C. Green. 2021. Multi-Agent Reinforcement Learning for Active Voltage Control on Power Distribution Networks. In NeurIPS. 3271\u20133284."},{"key":"e_1_3_2_2_28_1","volume-title":"A Survey on Large Language Model based Autonomous Agents. preprint arXiv:2308.11432","author":"Wang Lei","year":"2023","unstructured":"Lei Wang, Chen Ma, Xueyang Feng, Zeyu Zhang, Hao Yang, Jingsen Zhang, Zhiyuan Chen, Jiakai Tang, Xu Chen, Yankai Lin, 2023. A Survey on Large Language Model based Autonomous Agents. preprint arXiv:2308.11432 (2023)."},{"key":"e_1_3_2_2_29_1","volume-title":"A comprehensive survey of continual learning: Theory, method and application. preprint arXiv:2302.00487","author":"Wang Liyuan","year":"2023","unstructured":"Liyuan Wang, Xingxing Zhang, Hang Su, and Jun Zhu. 2023. A comprehensive survey of continual learning: Theory, method and application. preprint arXiv:2302.00487 (2023)."},{"key":"e_1_3_2_2_30_1","unstructured":"Maciej Wo\u0142czyk Micha\u0142 Zaj\u0105c Razvan Pascanu \u0141ukasz Kuci\u0144ski and Piotr Mi\u0142o\u015b. 2021. Continual world: A robotic benchmark for continual reinforcement learning. In NeurIPS. 28496\u201328510."},{"key":"e_1_3_2_2_31_1","volume-title":"Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution. preprint arXiv:2208.04957","author":"Xue Ke","year":"2022","unstructured":"Ke Xue, Yutong Wang, Lei Yuan, Cong Guan, Chao Qian, and Yang Yu. 2022. Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution. preprint arXiv:2208.04957 (2022)."},{"key":"e_1_3_2_2_32_1","unstructured":"Ke Xue Jiacheng Xu Lei Yuan Miqing Li Chao Qian Zongzhang Zhang and Yang Yu. 2022. Multi-agent dynamic algorithm configuration. In NeurIPS. 20147\u201320161."},{"key":"e_1_3_2_2_33_1","volume-title":"Multi-agent Continual Coordination via Progressive Task Contextualization. preprint arXiv:2305.13937","author":"Yuan Lei","year":"2023","unstructured":"Lei Yuan, Lihe Li, Ziqian Zhang, Fuxiang Zhang, Cong Guan, and Yang Yu. 2023. Multi-agent Continual Coordination via Progressive Task Contextualization. preprint arXiv:2305.13937 (2023)."},{"key":"e_1_3_2_2_34_1","volume-title":"A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment. preprint arXiv:2312.01058","author":"Yuan Lei","year":"2023","unstructured":"Lei Yuan, Ziqian Zhang, Lihe Li, Cong Guan, and Yang Yu. 2023. A Survey of Progress on Cooperative Multi-agent Reinforcement Learning in Open Environment. preprint arXiv:2312.01058 (2023)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"crossref","unstructured":"Lei Yuan Ziqian Zhang Ke Xue Hao Yin Feng Chen Cong Guan Lihe Li Chao Qian and Yang Yu. 2023. Robust multi-agent coordination via evolutionary generation of auxiliary adversarial attackers. In AAAI. 11753\u201311762.","DOI":"10.1609\/aaai.v37i10.26388"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwac123"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2900-0"},{"key":"e_1_3_2_2_38_1","volume-title":"Evolutionary learning: Advances in theories and algorithms","author":"Zhou Zhi-Hua","unstructured":"Zhi-Hua Zhou, Yang Yu, and Chao Qian. 2019. Evolutionary learning: Advances in theories and algorithms. Springer."}],"event":{"name":"DAI '23: The Fifth International Conference on Distributed Artificial Intelligence","location":"Singapore Singapore","acronym":"DAI '23"},"container-title":["The Fifth International Conference on Distributed Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627676.3627678","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3627676.3627678","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:26:21Z","timestamp":1756236381000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3627676.3627678"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,30]]},"references-count":38,"alternative-id":["10.1145\/3627676.3627678","10.1145\/3627676"],"URL":"https:\/\/doi.org\/10.1145\/3627676.3627678","relation":{},"subject":[],"published":{"date-parts":[[2023,11,30]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}