{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T19:13:11Z","timestamp":1789672391765,"version":"4.0.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T00:00:00Z","timestamp":1690329600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci. China Inf. Sci."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1007\/s11432-021-3479-9","type":"journal-article","created":{"date-parts":[[2023,7,27]],"date-time":"2023-07-27T22:01:36Z","timestamp":1690495296000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["LINDA: multi-agent local information decomposition for awareness of teammates"],"prefix":"10.1007","volume":"66","author":[{"given":"Jiahan","family":"Cao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaowei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongjie","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"De-Chuan","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,7,26]]},"reference":[{"key":"3479_CR1","first-page":"41","volume":"33","author":"K Tuyls","year":"2012","unstructured":"Tuyls K, Weiss G. Multiagent learning: basics, challenges, and prospects. AI Mag, 2012, 33: 41","journal-title":"AI Mag"},{"key":"3479_CR2","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1007\/s10462-021-09996-w","volume":"55","author":"S Gronauer","year":"2022","unstructured":"Gronauer S, Diepold K. Multi-agent deep reinforcement learning: a survey. Artif Intell Rev, 2022, 55: 895\u2013943","journal-title":"Artif Intell Rev"},{"key":"3479_CR3","doi-asserted-by":"publisher","first-page":"123805","DOI":"10.1109\/ACCESS.2021.3110255","volume":"9","author":"H Cui","year":"2021","unstructured":"Cui H, Zhang Z. A cooperative multi-agent reinforcement learning method based on coordination degree. IEEE Access, 2021, 9: 123805","journal-title":"IEEE Access"},{"key":"3479_CR4","unstructured":"OroojlooyJadid A, Hajinezhad D. A review of cooperative multi-agent deep reinforcement learning. 2019. ArXiv:1908.03963"},{"key":"3479_CR5","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1109\/TII.2012.2219061","volume":"9","author":"Y Cao","year":"2012","unstructured":"Cao Y, Yu W, Ren W, et al. An overview of recent progress in the study of distributed multi-agent coordination. IEEE Trans Ind Inf, 2012, 9: 427\u2013438","journal-title":"IEEE Trans Ind Inf"},{"key":"3479_CR6","unstructured":"Zhou M, Luo J, Villela J, et al. Smarts: scalable multi-agent reinforcement learning training school for autonomous driving. 2020. ArXiv:2010.09776"},{"key":"3479_CR7","series-title":"Reinforcement Learning","first-page":"441","volume-title":"Game theory and multi-agent reinforcement learning","author":"A Now\u00e9","year":"2012","unstructured":"Now\u00e9 A, Vrancx P, de Hauwere Y M. Game theory and multi-agent reinforcement learning. In: Reinforcement Learning. Berlin: Springer, 2012. 441\u2013470"},{"key":"3479_CR8","unstructured":"Christianos F, Sch\u00e4fer L, Albrecht S V. Shared experience actor-critic for multi-agent reinforcement learning. In: Proceedings of Advances in Neural Information Processing Systems, 2020"},{"key":"3479_CR9","unstructured":"Lyu X, Xiao Y, Daley B, et al. The contrasting centralized and decentralized critics in multi-agent reinforcement learning. In: Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems, 2021. 844\u2013852"},{"key":"3479_CR10","unstructured":"Sunehag P, Lever G, Gruslys A, et al. Value-decomposition networks for cooperative multi-agent learning based on team reward. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, 2018. 2085\u20132087"},{"key":"3479_CR11","unstructured":"Rashid T, Samvelyan M, de Witt C S, et al. QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of the 35th International Conference on Machine Learning, 2018. 4292\u20134301"},{"key":"3479_CR12","unstructured":"Wang J, Ren Z, Liu T, et al. QPLEX: duplex dueling multi-agent q-learning. In: Proceedings of the 9th International Conference on Learning Representations, 2021"},{"key":"3479_CR13","doi-asserted-by":"crossref","unstructured":"Wang J, Zhang Y, Kim T, et al. Shapley q-value: a local reward approach to solve global reward games. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence, 2020. 7285\u20137292","DOI":"10.1609\/aaai.v34i05.6220"},{"key":"3479_CR14","unstructured":"Wang T, Zeng L, Dong W, et al. Context-aware sparse deep coordination graphs. 2021. ArXiv:2106.02886"},{"key":"3479_CR15","unstructured":"Wang J, Wang J, Zhang Y, et al. SHAQ: incorporating shapley value theory into q-learning for multi-agent reinforcement learning. 2021. ArXiv:2105.15013"},{"key":"3479_CR16","unstructured":"Rashid T, Farquhar G, Peng B, et al. Weighted QMIX: expanding monotonic value function factorisation for deep multi-agent reinforcement learning. In: Proceedings of Advances in Neural Information Processing Systems, 2020"},{"key":"3479_CR17","doi-asserted-by":"crossref","unstructured":"Cho K, van Merrienboer B, G\u00fcl\u00e7ehre \u00c7, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2014. 1724\u20131734","DOI":"10.3115\/v1\/D14-1179"},{"key":"3479_CR18","doi-asserted-by":"crossref","unstructured":"Stone P, Kaminka G A, Kraus S, et al. Ad hoc autonomous agent teams: collaboration without pre-coordination. In: Proceedings of the 24th AAAI Conference on Artificial Intelligence, 2010","DOI":"10.1609\/aaai.v24i1.7529"},{"key":"3479_CR19","unstructured":"He H, Boyd-Graber J L. Opponent modeling in deep reinforcement learning. In: Proceedings of the 33rd International Conference on Machine Learning, 2016. 1804\u20131813"},{"key":"3479_CR20","unstructured":"Hong Z, Su S, Shann T, et al. A deep policy inference q-network for multi-agent systems. In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, 2018. 1388\u20131396"},{"key":"3479_CR21","unstructured":"Papoudakis G, Albrecht S V. Variational autoencoders for opponent modeling in multi-agent systems. 2020. ArXiv:2001.10829"},{"key":"3479_CR22","unstructured":"Papoudakis G, Christianos F, Albrecht S V. Local information opponent modelling using variational autoencoders. 2020. ArXiv:2006.09447"},{"key":"3479_CR23","unstructured":"Albrecht S V, Stone P. Reasoning about hypothetical agent behaviours and their parameters. In: Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems, 2017. 547\u2013555"},{"key":"3479_CR24","unstructured":"Vinyals O, Ewalds T, Bartunov S, et al. Starcraft II: a new challenge for reinforcement learning. 2017. ArXiv:1708.04782"},{"key":"3479_CR25","unstructured":"Samvelyan M, Rashid T, de Witt C S, et al. The starcraft multi-agent challenge. In: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, 2019. 2186\u20132188"},{"key":"3479_CR26","unstructured":"Lowe R, Wu Y, Tamar A, et al. Multi-agent actor-critic for mixed cooperative-competitive environments. In: Proceedings of Advances in Neural Information Processing Systems, 2017. 6379\u20136390"},{"key":"3479_CR27","doi-asserted-by":"crossref","unstructured":"Foerster J N, Farquhar G, Afouras T, et al. Counterfactual multi-agent policy gradients. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence, 2018. 2974\u20132982","DOI":"10.1609\/aaai.v32i1.11794"},{"key":"3479_CR28","unstructured":"Iqbal S, Sha F. Actor-attention-critic for multi-agent reinforcement learning. In: Proceedings of the 36th International Conference on Machine Learning, 2019. 2961\u20132970"},{"key":"3479_CR29","unstructured":"Son K, Kim D, Kang W J, et al. QTRAN: learning to factorize with transformation for cooperative multi-agent reinforcement learning. In: Proceedings of the 36th International Conference on Machine Learning, 2019. 5887\u20135896"},{"key":"3479_CR30","unstructured":"Wang T, Dong H, Lesser V R, et al. ROMA: multi-agent reinforcement learning with emergent roles. In: Proceedings of the 37th International Conference on Machine Learning, 2020. 9876\u20139886"},{"key":"3479_CR31","unstructured":"Wang T, Wang J, Zheng C, et al. Learning nearly decomposable value functions via communication minimization. In: Proceedings of the 8th International Conference on Learning Representations, 2020"},{"key":"3479_CR32","unstructured":"Wang T, Gupta T, Mahajan A, et al. RODE: learning roles to decompose multi-agent tasks. In: Proceedings of the 9th International Conference on Learning Representations, 2021"},{"key":"3479_CR33","unstructured":"Xie A, Losey D P, Tolsma R, et al. Learning latent representations to influence multi-agent interaction. In: Proceedings of the 4th Conference on Robot Learning, 2020. 575\u2013588"},{"key":"3479_CR34","unstructured":"Wang W, Yang T, Liu Y, et al. Action semantics network: considering the effects of actions in multiagent systems. In: Proceedings of the 8th International Conference on Learning Representations, 2020"},{"key":"3479_CR35","unstructured":"Zhang T, Xu H, Wang X, et al. Multi-agent collaboration via reward attribution decomposition. 2020. ArXiv:2010.08531"},{"key":"3479_CR36","unstructured":"Hu S, Zhu F, Chang X, et al. UPDeT: universal multi-agent reinforcement learning via policy decoupling with transformers. 2021. ArXiv:2101.08001"},{"key":"3479_CR37","doi-asserted-by":"crossref","unstructured":"Wu B. Hierarchical macro strategy model for MOBA game AI. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence, 2019. 1206\u20131213","DOI":"10.1609\/aaai.v33i01.33011206"},{"key":"3479_CR38","doi-asserted-by":"crossref","unstructured":"Palanisamy P. Multi-agent connected autonomous driving using deep reinforcement learning. In: Proceedings of International Joint Conference on Neural Networks, 2020. 1\u20137","DOI":"10.1109\/IJCNN48605.2020.9207663"},{"key":"3479_CR39","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","volume":"258","author":"S V Albrecht","year":"2018","unstructured":"Albrecht S V, Stone P. Autonomous agents modelling other agents: a comprehensive survey and open problems. Artif Intelligence, 2018, 258: 66\u201395","journal-title":"Artif Intelligence"},{"key":"3479_CR40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A Concise Introduction to Decentralized POMDPs","author":"F A Oliehoek","year":"2016","unstructured":"Oliehoek F A, Amato C. A Concise Introduction to Decentralized POMDPs. Berlin: Springer, 2016"},{"key":"3479_CR41","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1613\/jair.2447","volume":"32","author":"F A Oliehoek","year":"2008","unstructured":"Oliehoek F A, Spaan M T J, Vlassis N. Optimal and approximate q-value functions for decentralized POMDPs. J Artif Intell Res, 2008, 32: 289\u2013353","journal-title":"J Artif Intell Res"},{"key":"3479_CR42","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.01.031","volume":"190","author":"L Kraemer","year":"2016","unstructured":"Kraemer L, Banerjee B. Multi-agent reinforcement learning as a rehearsal for decentralized planning. Neurocomputing, 2016, 190: 82\u201394","journal-title":"Neurocomputing"},{"key":"3479_CR43","unstructured":"Kingma D P, Welling M. Auto-encoding variational bayes. 2013. ArXiv:1312.6114"},{"key":"3479_CR44","unstructured":"Alemi A A, Fischer I, Dillon J V, et al. Deep variational information bottleneck. In: Proceedings of the 5th International Conference on Learning Representations, 2017"},{"key":"3479_CR45","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten L, Hinton G. Visualizing data using t-SNE. J Mach Learn Res, 2008, 9: 2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"3479_CR46","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/S0004-3702(99)00025-9","volume":"110","author":"P Stone","year":"1999","unstructured":"Stone P, Veloso M. Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork. Artif Intell, 1999, 110: 241\u2013273","journal-title":"Artif Intell"},{"key":"3479_CR47","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1142\/S0218194018500043","volume":"28","author":"K M Lhaksmana","year":"2018","unstructured":"Lhaksmana K M, Murakami Y, Ishida T. Role-based modeling for designing agent behavior in self-organizing multi-agent systems. Int J Soft Eng Knowl Eng, 2018, 28: 79\u201396","journal-title":"Int J Soft Eng Knowl Eng"}],"container-title":["Science China Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-021-3479-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11432-021-3479-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11432-021-3479-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T16:22:32Z","timestamp":1726676552000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11432-021-3479-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,26]]},"references-count":47,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["3479"],"URL":"https:\/\/doi.org\/10.1007\/s11432-021-3479-9","relation":{},"ISSN":["1674-733X","1869-1919"],"issn-type":[{"value":"1674-733X","type":"print"},{"value":"1869-1919","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,26]]},"assertion":[{"value":"19 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"182101"}}