{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T08:10:32Z","timestamp":1758269432519},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030275341"},{"type":"electronic","value":"9783030275358"}],"license":[{"start":{"date-parts":[[2019,1,1]],"date-time":"2019-01-01T00:00:00Z","timestamp":1546300800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019]]},"DOI":"10.1007\/978-3-030-27535-8_48","type":"book-chapter","created":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T16:26:01Z","timestamp":1564676761000},"page":"533-543","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Multiagent Reinforcement Learning for Swarm Confrontation Environments"],"prefix":"10.1007","author":[{"given":"Guanyu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinhai","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huadong","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,8,2]]},"reference":[{"key":"48_CR1","unstructured":"Peng, P., Quan, Y., Ying, W., Yang, Y., Wang, J.: Multiagent bidirectionally-coordinated nets for learning to play StarCraft combat games (2017)"},{"issue":"4","key":"48_CR2","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1109\/TRO.2010.2048610","volume":"26","author":"E Besada-Portas","year":"2010","unstructured":"Besada-Portas, E., Torre, L.D.L., Cruz, J.M.D.L., Andr\u00e9s-Toro, B.D.: Evolutionary trajectory planner for multiple uavs in realistic scenarios. IEEE Trans. Robot. 26(4), 619\u2013634 (2010)","journal-title":"IEEE Trans. Robot."},{"key":"48_CR3","doi-asserted-by":"crossref","unstructured":"Fields, M.A., Haas, E., Hill, S., Stachowiak, C., Barnes, L.: Effective robot team control methodologies for battlefield applications. In: IEEE\/RSJ International Conference on Intelligent Robots & Systems (2009)","DOI":"10.1109\/IROS.2009.5354188"},{"issue":"7676","key":"48_CR4","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"7540","key":"48_CR5","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"M Volodymyr","year":"2015","unstructured":"Volodymyr, M., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"issue":"3\u20134","key":"48_CR6","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Mach. Learn. 8(3\u20134), 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"issue":"11","key":"48_CR7","first-page":"774","volume":"5","author":"J Peters","year":"2010","unstructured":"Peters, J., Bagnell, J.A.: Policy gradient methods. Encycl. Mach. Learn. 5(11), 774\u2013776 (2010)","journal-title":"Encycl. Mach. Learn."},{"key":"48_CR8","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1007\/978-3-642-14435-6_7","volume-title":"Innovations in Multi-Agent Systems and Applications - 1","author":"L Bu\u015foniu","year":"2010","unstructured":"Bu\u015foniu, L., Babu\u0161ka, R., De Schutter, B.: Multi-agent reinforcement learning: an overview. In: Srinivasan, D., Jain, L.C. (eds.) Innovations in Multi-Agent Systems and Applications - 1. SCI, vol. 310, pp. 183\u2013221. Springer, Heidelberg (2010). \n                      https:\/\/doi.org\/10.1007\/978-3-642-14435-6_7"},{"issue":"1","key":"48_CR9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0269888912000057","volume":"27","author":"L Matignon","year":"2012","unstructured":"Matignon, L., Laurent, G.J., Fort-Piat, N.L.: Independent reinforcement learners in cooperative Markov games: a survey regarding coordination problems. Knowl. Eng. Rev. 27(1), 1\u201331 (2012)","journal-title":"Knowl. Eng. Rev."},{"issue":"4","key":"48_CR10","doi-asserted-by":"publisher","first-page":"e0172395","DOI":"10.1371\/journal.pone.0172395","volume":"12","author":"A Tampuu","year":"2017","unstructured":"Tampuu, A., et al.: Multiagent cooperation and competition with deep reinforcement learning. Plos One 12(4), e0172395 (2017)","journal-title":"Plos One"},{"key":"48_CR11","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Neural Information Processing Systems (NIPS) (2017)"},{"key":"48_CR12","first-page":"26","volume":"35","author":"D Luo","year":"2017","unstructured":"Luo, D., Yang, X.U., Zhang, J.: New progresses on UAV swarm confrontation. Sci. Technol. Rev. 35, 26\u201331 (2017)","journal-title":"Sci. Technol. Rev."},{"key":"48_CR13","unstructured":"Yan, J., Minai, A.A., Polycarpou, M.M.: Cooperative real-time search and task allocation in UAV teams. In: IEEE Conference on Decision & Control (2003)"},{"issue":"2","key":"48_CR14","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., De Schutter, B.: A comprehensive survey of multiagent reinforcement learning. IEEE Trans. Syst. Man Cybern. Part C 38(2), 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C"},{"key":"48_CR15","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"S Pan","year":"2010","unstructured":"Pan, S., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22, 1345\u20131359 (2010)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"10","key":"48_CR16","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M.E., Stone, P.: Transfer learning for reinforcement learning domains: a survey. J. Mach. Learn. Res. 10(10), 1633\u20131685 (2009)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"48_CR17","first-page":"62","volume":"26","author":"MR Genesereth","year":"2005","unstructured":"Genesereth, M.R., Love, N., Pell, B.: General game playing: overview of the aaai competition. AI Mag. 26(2), 62\u201372 (2005)","journal-title":"AI Mag."},{"key":"48_CR18","unstructured":"Heinrich, J., Silver, D.: Deep reinforcement learning from self-play in imperfect-information games (2016)"},{"key":"48_CR19","first-page":"1","volume":"94","author":"L Babel","year":"2018","unstructured":"Babel, L.: Coordinated target assignment and UAV path planning with timing constraints. J. Intell. Robot. Syst. 94, 1\u201313 (2018)","journal-title":"J. Intell. Robot. Syst."}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-27535-8_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,1]],"date-time":"2019-08-01T17:00:24Z","timestamp":1564678824000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-27535-8_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030275341","9783030275358"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-27535-8_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2019]]},"assertion":[{"value":"2 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenyang","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 August 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.icira2019.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}