{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T14:50:56Z","timestamp":1782399056399,"version":"3.54.5"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2021,1,16]],"date-time":"2021-01-16T00:00:00Z","timestamp":1610755200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,16]],"date-time":"2021-01-16T00:00:00Z","timestamp":1610755200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Key Research and Development Program of China","award":["No.2017YFB1001901"],"award-info":[{"award-number":["No.2017YFB1001901"]}]},{"name":"Key Program of Tianjin Science and Technology Development Plan","award":["No.18ZXZNGX00120"],"award-info":[{"award-number":["No.18ZXZNGX00120"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["No.2018M643900"],"award-info":[{"award-number":["No.2018M643900"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s10489-020-02065-9","type":"journal-article","created":{"date-parts":[[2021,1,16]],"date-time":"2021-01-16T12:02:26Z","timestamp":1610798546000},"page":"5793-5808","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Multi-agent deep reinforcement learning with type-based hierarchical group communication"],"prefix":"10.1007","volume":"51","author":[{"given":"Hao","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dianxi","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Xue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gongju","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongjun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,1,16]]},"reference":[{"issue":"1851","key":"2065_CR1","doi-asserted-by":"publisher","first-page":"20162326","DOI":"10.1098\/rspb.2016.2326","volume":"284","author":"A Bear","year":"2017","unstructured":"Bear A, Kagan A, Rand DG (2017) Co-evolution of cooperation and cognition: the impact of imperfect deliberation and context-sensitive intuition. Proc Royal Soc B Biol Sci 284(1851):20162326","journal-title":"Proc Royal Soc B Biol Sci"},{"key":"2065_CR2","doi-asserted-by":"crossref","unstructured":"Bresciani PG, Giunchiglia P, Mylopoulos F, Perini J, TROPOS A (2004) An agent oriented software development methodology. Journal of autonomous agents and multiagent systems, Kluwer Academic Publishers","DOI":"10.1023\/B:AGNT.0000018806.20944.ef"},{"key":"2065_CR3","unstructured":"Butler E (2012) The condensed wealth of nations. Centre for Independent Studies"},{"key":"2065_CR4","unstructured":"Carion N, Usunier N, Synnaeve G, Lazaric A (2019) A structured prediction approach for generalization in cooperative multi-agent reinforcement learning. In: Advances in neural information processing systems, pp 8130\u20138140"},{"key":"2065_CR5","doi-asserted-by":"crossref","unstructured":"Chen Y, Zhou M, Wen Y, Yang Y, Su Y, Zhang W, Zhang D, Wang J, Liu H (2018) Factorized q-learning for large-scale multi-agent systems. arXiv:1809.03738","DOI":"10.1145\/3356464.3357707"},{"issue":"09","key":"2065_CR6","first-page":"1996","volume":"40","author":"L Chuang","year":"2017","unstructured":"Chuang L, Chao X, Jie H, Wenzhuo L, et al. (2017) Hierarchical architecture design of computer system. Chinese J Comput 40(09):1996\u20132017","journal-title":"Chinese J Comput"},{"key":"2065_CR7","unstructured":"Clevert DA, Unterthiner T, Hochreiter S (2015) Fast and accurate deep network learning by exponential linear units (elus). arXiv:1511.07289"},{"key":"2065_CR8","doi-asserted-by":"crossref","unstructured":"Cossentino M, Gaglio S, Sabatucci L, Seidita V (2005) The passi and agile passi mas meta-models compared with a unifying proposal. In: International central and eastern european conference on multi-agent systems, pp 183\u2013192. Springer","DOI":"10.1007\/11559221_19"},{"key":"2065_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39975-6","volume-title":"Handbook on agent-oriented design processes","author":"M Cossentino","year":"2014","unstructured":"Cossentino M, Hilaire V, Molesini A, Seidita V (2014) Handbook on agent-oriented design processes. Springer, Berlin"},{"key":"2065_CR10","unstructured":"Das A, Gervet T, Romoff J, Batra D, Parikh D, Rabbat M, Pineau J (2018) Tarmac: Targeted multi-agent communication. arXiv:1810.11187"},{"issue":"Jun","key":"2065_CR11","first-page":"1239","volume":"10","author":"C Dugas","year":"2009","unstructured":"Dugas C, Bengio Y, B\u00e9lisle F., Nadeau C, Garcia R (2009) Incorporating functional knowledge in neural networks. J Mach Learn Res 10(Jun):1239\u20131262","journal-title":"J Mach Learn Res"},{"key":"2065_CR12","doi-asserted-by":"crossref","unstructured":"Foerster JN, Farquhar G, Afouras T, Nardelli N, Whiteson S (2018) Counterfactual multi-agent policy gradients. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11794"},{"issue":"6570","key":"2065_CR13","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1038\/380121a0","volume":"380","author":"DM Gordon","year":"1996","unstructured":"Gordon DM (1996) The organization of work in social insect colonies. Nature 380(6570):121\u2013124","journal-title":"Nature"},{"key":"2065_CR14","unstructured":"Ha D, Dai A, Le QV (2016) Hypernetworks. arXiv:1609.09106"},{"issue":"1","key":"2065_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1186\/s13015-016-0074-8","volume":"11","author":"R Henriques","year":"2016","unstructured":"Henriques R, Madeira SC (2016) Bicnet: Flexible module discovery in large-scale biological networks using biclustering. Algorithms Mol Biol 11(1):14","journal-title":"Algorithms Mol Biol"},{"issue":"8","key":"2065_CR16","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computat 9(8):1735\u20131780","journal-title":"Neural Computat"},{"key":"2065_CR17","unstructured":"Iqbal S, Sha F (2018) Actor-attention-critic for multi-agent reinforcement learning. arXiv:1810.02912"},{"issue":"5","key":"2065_CR18","doi-asserted-by":"publisher","first-page":"1183","DOI":"10.1016\/j.anbehav.2005.03.004","volume":"70","author":"R Jeanson","year":"2005","unstructured":"Jeanson R, Kukuk PF, Fewell JH (2005) Emergence of division of labour in halictine bees: contributions of social interactions and behavioural variance. Anim Behav 70(5):1183\u20131193","journal-title":"Anim Behav"},{"key":"2065_CR19","unstructured":"Jiang J, Dun C, Lu Z (2018) Graph convolutional reinforcement learning for multi-agent cooperation. arXiv:1810.09202,2(3)"},{"key":"2065_CR20","unstructured":"Jiang J, Lu Z (2018) Learning attentional communication for multi-agent cooperation. In: Advances in neural information processing systems, pp 7254\u20137264"},{"key":"2065_CR21","unstructured":"Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv:1412.6980"},{"key":"2065_CR22","doi-asserted-by":"crossref","unstructured":"Liu Y, Hu Y, Gao Y, Chen Y, Fan C (2019) Value function transfer for deep multi-agent reinforcement learning based on n-step returns. In: Proceedings of the twenty-eighth international joint conference on artificial intelligence, pp 457\u2013463","DOI":"10.24963\/ijcai.2019\/65"},{"key":"2065_CR23","doi-asserted-by":"crossref","unstructured":"Liu Y, Wang W, Hu Y, Hao J, Chen X, Gao Y (2019) Multi-agent game abstraction via graph attention neural network. arXiv:1911.10715","DOI":"10.1609\/aaai.v34i05.6211"},{"key":"2065_CR24","unstructured":"Long Q, Zhou Z, Gupta A, Fang F, Wu Y, Wang X (2020) Evolutionary population curriculum for scaling multi-agent reinforcement learning. arXiv:2003.10423"},{"key":"2065_CR25","unstructured":"Lowe R, Wu YI, Tamar A, Harb J, Abbeel OP, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in neural information processing systems, pp 6379\u20136390"},{"key":"2065_CR26","unstructured":"Mao H, Liu W, Hao J, Luo J, Li D, Zhang Z, Wang J, Xiao Z (2019) Neighborhood cognition consistent multi-agent reinforcement learning. arXiv:1912.01160"},{"issue":"11","key":"2065_CR27","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1016\/j.artint.2011.05.001","volume":"175","author":"FS Melo","year":"2011","unstructured":"Melo FS, Veloso M (2011) Decentralized mdps with sparse interactions. Artif Intell 175 (11):1757\u20131789","journal-title":"Artif Intell"},{"issue":"7540","key":"2065_CR28","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih V, Kavukcuoglu K, Silver D, Rusu AA, Veness J, Bellemare MG, Graves A, Riedmiller M, Fidjeland AK, Ostrovski G et al (2015) Human-level control through deep reinforcement learning. Nature 518(7540):529\u2013533","journal-title":"Nature"},{"key":"2065_CR29","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: ICML"},{"key":"2065_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-28929-8","volume-title":"A concise introduction to decentralized POMDPs, vol 1","author":"FA Oliehoek","year":"2016","unstructured":"Oliehoek FA, Amato C, et al. (2016) A concise introduction to decentralized POMDPs, vol 1. Springer, Berlin"},{"key":"2065_CR31","unstructured":"OroojlooyJadid A, Hajinezhad D (2019) A review of cooperative multi-agent deep reinforcement learning. arXiv:1908.03963"},{"key":"2065_CR32","doi-asserted-by":"crossref","unstructured":"Pal SK, Mitra S (1992) Multilayer perceptron, fuzzy sets classifiaction","DOI":"10.1109\/72.159058"},{"key":"2065_CR33","doi-asserted-by":"crossref","unstructured":"Ryu H, Shin H, Park J (2020) Multi-agent actor-critic with hierarchical graph attention network. In: AAAI, pp 7236\u20137243","DOI":"10.1609\/aaai.v34i05.6214"},{"key":"2065_CR34","unstructured":"Samvelyan M, Rashid T, de Witt CS, Farquhar G, Nardelli N, Rudner TG, Hung CM, Torr PH, Foerster J, Whiteson S (2019) The starcraft multi-agent challenge. arXiv:1902.04043"},{"key":"2065_CR35","unstructured":"Schulman J, Wolski F, Dhariwal P, Radford A, Klimov O (2017) Proximal policy optimization algorithms. arXiv:1707.06347"},{"key":"2065_CR36","unstructured":"Singh A, Jain T, Sukhbaatar S (2018) Learning when to communicate at scale in multiagent cooperative and competitive tasks. arXiv:1812.09755"},{"key":"2065_CR37","unstructured":"Son K, Kim D, Kang WJ, Hostallero DE, Yi Y (2019) Qtran: Learning to factorize with transformation for cooperative multi-agent reinforcement learning. arXiv:1905.05408"},{"issue":"3","key":"2065_CR38","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone P, Veloso M (2000) Multiagent systems: a survey from a machine learning perspective. Auton Robot 8(3):345\u2013383","journal-title":"Auton Robot"},{"key":"2065_CR39","unstructured":"Sukhbaatar S, Fergus R, et al. (2016) Learning multiagent communication with backpropagation. In: Advances in neural information processing systems, pp 2244\u20132252"},{"key":"2065_CR40","unstructured":"Sunehag P, Lever G, Gruslys A, Czarnecki WM, Zambaldi V, Jaderberg M, Lanctot M, Sonnerat N, Leibo JZ, Tuyls K et al (2017) Value-decomposition networks for cooperative multi-agent learning. arXiv:1706.05296"},{"key":"2065_CR41","unstructured":"Sutton RS, McAllester DA, Singh SP, Mansour Y (2000) Policy gradient methods for reinforcement learning with function approximation. In: Advances in neural information processing systems, pp 1057\u20131063"},{"key":"2065_CR42","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv:1710.10903"},{"key":"2065_CR43","doi-asserted-by":"crossref","unstructured":"Wang W, Yang T, Liu Y, Hao J, Hao X, Hu Y, Chen Y, Fan C, Gao Y (2020) From few to more: large-scale dynamic multiagent curriculum learning. In: AAAI, pp 7293\u20137300","DOI":"10.1609\/aaai.v34i05.6221"},{"issue":"10","key":"2065_CR44","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","volume":"78","author":"PJ Werbos","year":"1990","unstructured":"Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78 (10):1550\u20131560","journal-title":"Proc IEEE"},{"key":"2065_CR45","unstructured":"Whiteson S (2018) Qmix: Monotonic value function factorisation for deep multi- agent reinforcement learning"},{"issue":"3","key":"2065_CR46","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1023\/A:1010071910869","volume":"3","author":"M Wooldridge","year":"2000","unstructured":"Wooldridge M, Jennings NR, Kinny D (2000) The gaia methodology for agent-oriented analysis and design. Auton Agents Multi-Agent Syst 3(3):285\u2013312","journal-title":"Auton Agents Multi-Agent Syst"},{"key":"2065_CR47","unstructured":"Yang Y, Luo R, Li M, Zhou M, Zhang W, Wang J (2018) Mean field multi-agent reinforcement learning. arXiv:1802.05438"},{"issue":"12","key":"2065_CR48","doi-asserted-by":"publisher","first-page":"2853","DOI":"10.1109\/TCYB.2014.2387277","volume":"45","author":"C Yu","year":"2015","unstructured":"Yu C, Zhang M, Ren F, Tan G (2015) Multiagent learning of coordination in loosely coupled multiagent systems. IEEE Trans Cybern 45(12):2853\u20132867","journal-title":"IEEE Trans Cybern"},{"key":"2065_CR49","unstructured":"Zhang Z, Yang J, Zha H (2019) Integrating independent and centralized multi-agent reinforcement learning for traffic signal network optimization. arXiv:1909.10651"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-02065-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-020-02065-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-02065-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,11]],"date-time":"2022-12-11T22:43:13Z","timestamp":1670798593000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-020-02065-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,16]]},"references-count":49,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["2065"],"URL":"https:\/\/doi.org\/10.1007\/s10489-020-02065-9","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,16]]},"assertion":[{"value":"4 November 2020","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 January 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}