{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T16:59:39Z","timestamp":1774025979024,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T00:00:00Z","timestamp":1594684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T00:00:00Z","timestamp":1594684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"National Key R&D Program of China","award":["2017YFB1002505"],"award-info":[{"award-number":["2017YFB1002505"]}]},{"name":"National Key R&D Program of China","award":["2018YFB1305101"],"award-info":[{"award-number":["2018YFB1305101"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2020,12]]},"DOI":"10.1007\/s10489-020-01755-8","type":"journal-article","created":{"date-parts":[[2020,7,14]],"date-time":"2020-07-14T05:29:00Z","timestamp":1594704540000},"page":"4195-4205","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["GAMA: Graph Attention Multi-agent reinforcement learning algorithm for cooperation"],"prefix":"10.1007","volume":"50","author":[{"given":"Haoqiang","family":"Chen","sequence":"first","affiliation":[]},{"given":"Yadong","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Zongtan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Dewen","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,7,14]]},"reference":[{"key":"1755_CR1","unstructured":"Battaglia PW, Hamrick JB, Bapst V, Sanchez-Gonzalez A, Zambaldi V, Mali-nowski M, Tacchetti A, Raposo D, Santoro A, Faulkner R (2018) Relational inductive biases, deep learning and graph networks"},{"key":"1755_CR2","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) Openai gym"},{"issue":"52","key":"1755_CR3","first-page":"1436574","volume":"27","author":"H Demis","year":"2007","unstructured":"Demis H, Dharshan K, Maguire EA (2007) Using imagination to understand the neural basis of episodic memory. Journal of Neuroscience the Official Journal of the Society for Neuroscience 27(52):1436574","journal-title":"Journal of Neuroscience the Official Journal of the Society for Neuroscience"},{"issue":"6198","key":"1755_CR4","doi-asserted-by":"publisher","first-page":"795","DOI":"10.1126\/science.1254295","volume":"345","author":"M Rubenstein","year":"2014","unstructured":"Rubenstein M, Cornejo A, Nagpal R (2014) Programmable self-assembly in a thousand-robot swarm. Science 345(6198):795\u2013799","journal-title":"Science"},{"issue":"6172","key":"1755_CR5","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1126\/science.1245842","volume":"343","author":"J Werfel","year":"2014","unstructured":"Werfel J, Petersen K, Nagpal R (2014) Designing collective behavior in a termite-inspired robot construction team. Science 343(6172):754\u2013758","journal-title":"Science"},{"key":"1755_CR6","doi-asserted-by":"publisher","first-page":"1075","DOI":"10.1080\/0952813X.2015.1056241","volume":"28.6","author":"MEH Souidi","year":"2016","unstructured":"Souidi MEH, et al. (2016) \u201cMulti-agent cooperation pursuit based on an extension of AALAADIN organisational model\u201d. Journal of Experimental & Theoretical Artificial Intelligence 28.6:1075\u20131088","journal-title":"Journal of Experimental & Theoretical Artificial Intelligence"},{"key":"1755_CR7","doi-asserted-by":"crossref","unstructured":"Kotb Y, Ridhawi I, Aloqaily M, Baker T, Jararweh Y, Tawfik H (2019) Cloud-Based Multi-Agent Cooperation for IoT Devices Using Workflow-Nets, vol 17","DOI":"10.1007\/s10723-019-09485-z"},{"key":"1755_CR8","unstructured":"Singh AJ, Kumar A (2019) Graph based optimization for multiagent cooperation. In: Proceedings of the 18th International Conference on Autonomous Agents and Multiagent Systems (AAMAS), Montreal, Canada, May 13-17. 1497-1505. Research Collection School Of Information Systems"},{"issue":"3","key":"1755_CR9","first-page":"171\u2014190","volume":"5","author":"F Buccafurri","year":"2004","unstructured":"Buccafurri F, Palopoli L, Rosaci D, Sarn\u00e8 GML (2004) Modeling Cooperation in Multi-Agent Communities. Cognitive Systems Research Journal (CSRJ) (lavoro invitato) 5(3):171\u2014190. Elsevier","journal-title":"Cognitive Systems Research Journal (CSRJ) (lavoro invitato)"},{"issue":"6","key":"1755_CR10","doi-asserted-by":"publisher","first-page":"793","DOI":"10.1016\/j.is.2006.06.003","volume":"32","author":"D Rosaci","year":"2007","unstructured":"Rosaci D (2007) CILIOS : Connectionist Inductive Learning And Inter-Ontology Similarities for Recommending Information Agents. Information Systems 32(6):793\u2013825 . Elsevier","journal-title":"Information Systems"},{"key":"1755_CR11","doi-asserted-by":"crossref","unstructured":"Diestel R (2013) Graph Theory","DOI":"10.4171\/OWR\/2013\/02"},{"key":"1755_CR12","unstructured":"Guttenberg N, Yu Y, Kanai R (2017) Counterfactual control for free from generative models"},{"key":"1755_CR13","unstructured":"Henderson P, Islam R, Bachman P, Pineau J, Precup D, Meger D (2017) Deep reinforcement learning that matters. arXiv:1709.06560"},{"key":"1755_CR14","unstructured":"Iqbal S, Sha F (2018) Actor-attention-critic for multi-agent reinforcement learning. arXiv:1810.02912"},{"key":"1755_CR15","unstructured":"Kingma DP, Ba J (2014) Adam:, A method for stochastic optimization. arXiv:1412.6980"},{"key":"1755_CR16","doi-asserted-by":"crossref","unstructured":"Konda V, Tsitsiklis J (2001) Actor-critic algorithms, vol 42","DOI":"10.1137\/S0363012901385691"},{"key":"1755_CR17","unstructured":"Li Y (2017) Deep reinforcement learning: An overview. arXiv:1701.07274"},{"key":"1755_CR18","unstructured":"Lowe R, Wu Y, Tamar A, Harb J, Abbeel P, Mordatch I (2017) Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, 4-9 December 2017, Long Beach, CA, USA, pp. 63796390. http:\/\/papers.nips.cc\/paper\/7217-multi-agent-actor-critic-for-mixed-cooperative-competitive-environments"},{"key":"1755_CR19","unstructured":"Raileanu R, Denton E, Szlam A, Fergus R (2018) Modeling others using oneself in multi-agent reinforcement learning. arXiv:1802.09640"},{"issue":"4","key":"1755_CR20","doi-asserted-by":"publisher","first-page":"677694","DOI":"10.1016\/j.neuron.2012.11.001","volume":"76","author":"DL Schacter","year":"2012","unstructured":"Schacter DL, Addis DR, Hassabis D, Martin VC, Spreng RN, Szpunar KK (2012) The future of memory: Remembering, imagining, and the brain. Neuron 76(4):677694","journal-title":"Neuron"},{"key":"1755_CR21","doi-asserted-by":"crossref","unstructured":"Shi W, Song S, Wu C (2019) Soft policy gradient method for maximum entropy deep reinforcement learning. pp 34253431","DOI":"10.24963\/ijcai.2019\/475"},{"key":"1755_CR22","doi-asserted-by":"crossref","unstructured":"Busoniu L, Babu Ska R, Schutter BD (2010) Multi-agent reinforcement learning: An overview","DOI":"10.1109\/ADPRL.2011.5967353"},{"key":"1755_CR23","first-page":"487494","volume-title":"Readings in agents. chap. Multi-agent Reinforcement learning: Independent vs.Cooperative Agents","author":"M Tan","year":"1998","unstructured":"Tan M (1998) Readings in agents. chap. Multi-agent Reinforcement learning: Independent vs.Cooperative Agents. Morgan Kaufmann Publishers Inc, San Francisco, CA, USA, p 487494. http:\/\/dl.acm.org\/citation.cfm?id=284860.284934"},{"key":"1755_CR24","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv:1706.03762"},{"key":"1755_CR25","unstructured":"Velikovi P, Cucurull G, Casanova A, Romero A, Li P, Bengio Y (2018) Graph attention networks. In: International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=rJXMpikCZ"},{"issue":"3-4","key":"1755_CR26","doi-asserted-by":"publisher","first-page":"229256","DOI":"10.1007\/BF00992696","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams RJ (1992) Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning 8(3-4):229256","journal-title":"Machine Learning"},{"key":"1755_CR27","doi-asserted-by":"crossref","unstructured":"Zhu Y, Mottaghi R, Kolve E, Lim JJ, Farhadi A (2017) Target-driven visual navigation in indoor scenes using deep reinforcement learning. In: IEEE International conference on robotics & automation","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"1755_CR28","unstructured":"Ackermann J, Gabler V, Osa T, Sugiyama M (2019) Reducing overestimation bias in multi-agent domains using double centralized critics"},{"key":"1755_CR29","first-page":"285286","volume":"16","author":"RS Sutton","year":"1988","unstructured":"Sutton RS, Barto AG (1988) Reinforcement learning: an introduction. IEEE Transactions on Neural Networks 16:285286","journal-title":"IEEE Transactions on Neural Networks"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-01755-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-020-01755-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-020-01755-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,13]],"date-time":"2021-07-13T23:40:58Z","timestamp":1626219658000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-020-01755-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,14]]},"references-count":29,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["1755"],"URL":"https:\/\/doi.org\/10.1007\/s10489-020-01755-8","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,14]]},"assertion":[{"value":"14 July 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}