{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:35Z","timestamp":1763191715188,"version":"3.45.0"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11228126","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Pattern Extraction Learning for Cooperative Multi-Agent Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Yifan","family":"Zang","sequence":"first","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}]},{"given":"Jinmin","family":"He","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}]},{"given":"Junliang","family":"Xing","sequence":"additional","affiliation":[{"name":"Tsinghua University"}]},{"given":"Jian","family":"Cheng","sequence":"additional","affiliation":[{"name":"Institute of Automation,Chinese Academy of Sciences"}]}],"member":"263","reference":[{"year":"2017","author":"H\u00fcttenrauch","article-title":"Guided deep reinforcement learning for swarm systems","key":"ref1"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1109\/ICCA.2018.8444355"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TITS.2019.2901791"},{"doi-asserted-by":"publisher","key":"ref4","DOI":"10.1109\/TVT.2020.2997896"},{"doi-asserted-by":"publisher","key":"ref5","DOI":"10.1109\/TPWRS.2020.2999890"},{"key":"ref6","first-page":"3271","article-title":"Multi-agent reinforcement learning for active voltage control on power distribution networks","volume":"34","author":"Wang","year":"2021"},{"doi-asserted-by":"publisher","key":"ref7","DOI":"10.1007\/s10462-021-09996-w"},{"year":"2019","author":"OroojlooyJadid","article-title":"A review of cooperative multi-agent deep reinforcement learning","key":"ref8"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"year":"2021","author":"Yu","article-title":"The surprising effectiveness of ppo in cooperative multi-agent games","key":"ref10"},{"doi-asserted-by":"publisher","key":"ref11","DOI":"10.1007\/s10458-019-09421-1"},{"doi-asserted-by":"publisher","key":"ref12","DOI":"10.1007\/978-3-030-60990-0_12"},{"doi-asserted-by":"publisher","key":"ref13","DOI":"10.1016\/j.neucom.2016.01.031"},{"doi-asserted-by":"publisher","key":"ref14","DOI":"10.1007\/978-3-319-28929-8"},{"key":"ref15","first-page":"2085","article-title":"Value-decomposition networks for cooperative multi-agent learning based on team reward","volume-title":"International Conference on Autonomous Agents and Multi-Agent Systems","author":"Sunehag"},{"key":"ref16","article-title":"Vast: Value function factorization with variable agent sub-teams","volume":"34","author":"Phan","year":"2021"},{"key":"ref17","first-page":"5887","article-title":"Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Son"},{"volume-title":"International Conference on Learning Representations","author":"Wang","article-title":"Qplex: Duplex dueling multi-agent q-learning","key":"ref18"},{"volume-title":"International Conference on Machine Learning","author":"Wan","article-title":"Greedy based value representation for optimal coordination in multi-agent reinforcement learning","key":"ref19"},{"key":"ref20","first-page":"7611","article-title":"Maven: Multi-agent variational exploration","author":"Mahajan","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"Li","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","article-title":"The starcraft multi-agent challenge","author":"Samvelyan","year":"2019","journal-title":"CoRR"},{"key":"ref23","first-page":"4295","article-title":"Qmix: Monotonic value function factorisation for deep multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rashid"},{"key":"ref24","first-page":"3930","article-title":"Uneven: Universal value exploration for multi-agent reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Gupta"},{"key":"ref25","first-page":"10 199","article-title":"Weighted qmix: Expanding monotonic value function factorisation","author":"Rashid","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"10 571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","author":"Zhang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1631\/FITEE.2100594"},{"year":"2020","author":"Yang","article-title":"Qatten: A general framework for cooperative multiagent reinforcement learning","key":"ref28"},{"volume-title":"International Conference on Machine Learning","author":"Yang","article-title":"Q-value path decomposition for deep multiagent reinforcement learning","key":"ref29"},{"doi-asserted-by":"publisher","key":"ref30","DOI":"10.1609\/aaai.v35i13.17353"},{"doi-asserted-by":"publisher","key":"ref31","DOI":"10.1142\/S0218194018500043"},{"doi-asserted-by":"publisher","key":"ref32","DOI":"10.1609\/aaai.v34i05.6212"},{"key":"ref33","article-title":"Ldsa: Learning dynamic subtask assignment in cooperative multi-agent reinforcement learning","author":"Yang","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"volume-title":"NeurIPS","author":"Iqbal","article-title":"Alma: Hierarchical learning for composite multi-agent tasks","key":"ref34"},{"volume-title":"International Conference on Learning Representations","author":"Hu","article-title":"Updet: Universal multi-agent reinforcement learning via policy decoupling with transformers","key":"ref35"},{"volume-title":"International Conference on Machine Learning","author":"Iqbal","article-title":"Randomized entity-wise factorization for multi-agent reinforcement learning","key":"ref36"},{"key":"ref37","first-page":"9876","article-title":"Roma: Multi-agent reinforcement learning with emergent roles","volume-title":"International Conference on Machine Learning","author":"Wang"},{"volume-title":"International Conference on Learning Representations","author":"Wang","article-title":"Rode: Learning roles to decompose multi-agent tasks","key":"ref38"},{"key":"ref39","article-title":"Automatic grouping for efficient cooperative multi-agent reinforcement learning","volume":"36","author":"Zang","year":"2024"},{"key":"ref40","article-title":"Multi-agent common knowledge reinforcement learning","volume":"32","author":"de Witt","year":"2019","journal-title":"Advances in neural information processing systems"},{"doi-asserted-by":"publisher","key":"ref41","DOI":"10.1609\/aaai.v32i1.11794"},{"volume-title":"International conference on machine learning","author":"Iqbal","article-title":"Actor-attention-critic for multi-agent reinforcement learning","key":"ref42"},{"key":"ref43","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref44","first-page":"1614","article-title":"From softmax to sparsemax: A sparse model of attention and multi-label classification","volume-title":"International Conference on Machine Learning","author":"Martins"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1109\/TPAMI.2024.3399936"},{"year":"2021","author":"Hu","article-title":"Riit: Rethinking the importance of implementation tricks in multi-agent reinforcement learning","key":"ref46"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11228126.pdf?arnumber=11228126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:26:38Z","timestamp":1763191598000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11228126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11228126","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}