{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T07:01:39Z","timestamp":1726038099033},"publisher-location":"Cham","reference-count":14,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030263539"},{"type":"electronic","value":"9783030263546"}],"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\/978-3-030-26354-6_1","type":"book-chapter","created":{"date-parts":[[2019,7,18]],"date-time":"2019-07-18T12:02:47Z","timestamp":1563451367000},"page":"3-10","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multi-robot Cooperation Strategy in a Partially Observable Markov Game Using Enhanced Deep Deterministic Policy Gradient"],"prefix":"10.1007","author":[{"given":"Qirong","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingtao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fangchao","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengjie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,7,19]]},"reference":[{"issue":"1","key":"1_CR1","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s11370-017-0237-6","volume":"11","author":"AD Nuovo","year":"2018","unstructured":"Nuovo, A.D., et al.: The multi-modal interface of robot-era multi-robot services tailored for the elderly. Intell. Serv. Rob. 11(1), 109\u2013126 (2018)","journal-title":"Intell. Serv. Rob."},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Schmuck, P., Chli, M.: Multi-UAV collaborative monocular SLAM. In: International Conference on Robotics and Automation, pp. 3863\u20133870. Singapore (2017)","DOI":"10.1109\/ICRA.2017.7989445"},{"key":"1_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1007\/978-3-319-93818-9_10","volume-title":"Advances in Swarm Intelligence","author":"W Luo","year":"2018","unstructured":"Luo, W., Tang, Q., Fu, C., Eberhard, P.: Deep-sarsa based multi-UAV path planning and obstacle avoidance in a dynamic environment. In: Tan, Y., Shi, Y., Tang, Q. (eds.) ICSI 2018. LNCS, vol. 10942, pp. 102\u2013111. Springer, Cham (2018). \n                      https:\/\/doi.org\/10.1007\/978-3-319-93818-9_10"},{"key":"1_CR4","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.eswa.2018.08.008","volume":"115","author":"N Milad","year":"2019","unstructured":"Milad, N., Esmaeel, K., Samira, D.: Multi-objective multi-robot path planning in continuous environment using an enhanced genetic algorithm. Expert Syst. Appl. 115, 106\u2013120 (2019)","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"1_CR5","first-page":"1334","volume":"17","author":"S Levine","year":"2015","unstructured":"Levine, S., Finn, C., Darrell, T., Abbeel, P.: End-to-end training of deep visuomotor policies. J. Mach. Learn. Res. 17(1), 1334\u20131373 (2015)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Tan, M.: Multi-agent reinforcement learning: independent vs. cooperative agents. In: International Conference on Machine Learning, Amherst, USA, pp. 330\u2013337 (1993)","DOI":"10.1016\/B978-1-55860-307-3.50049-6"},{"issue":"1","key":"1_CR7","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."},{"key":"1_CR8","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/j.engappai.2016.11.008","volume":"58","author":"J Hao","year":"2017","unstructured":"Hao, J., Huang, D., Yi, C., Leung, H.F.: The dynamics of reinforcement social learning in networked cooperative multiagent systems. Eng. Appl. Artif. Intell. 58, 111\u2013122 (2017)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1_CR9","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1007\/978-3-319-71682-4_5","volume-title":"Autonomous Agents and Multiagent Systems","author":"JK Gupta","year":"2017","unstructured":"Gupta, J.K., Egorov, M., Kochenderfer, M.: Cooperative multi-agent control using deep reinforcement learning. In: Sukthankar, G., Rodriguez-Aguilar, J.A. (eds.) AAMAS 2017. LNCS (LNAI), vol. 10642, pp. 66\u201383. Springer, Cham (2017). \n                      https:\/\/doi.org\/10.1007\/978-3-319-71682-4_5"},{"issue":"4","key":"1_CR10","first-page":"357","volume":"182","author":"B Fan","year":"2005","unstructured":"Fan, B., Pan, Q., Zhang, H.C.: A multi-agent coordination method based on Markov game and application to robot soccer. Robotics 182(4), 357\u2013366 (2005)","journal-title":"Robotics"},{"key":"1_CR11","unstructured":"Foerster, J.N., Assael, Y.M., Freitas, N.D., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: International Conference on Neural Information Processing Systems, Barcelo, Spain, pp. 2137\u20132145 (2016)"},{"issue":"3","key":"1_CR12","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/BF00940310","volume":"59","author":"GJ Olsder","year":"1988","unstructured":"Olsder, G.J., Papavassilopoulos, G.P.: A Markov chain game with dynamic information. J. Optim. Theor. Appl. 59(3), 467\u2013486 (1988)","journal-title":"J. Optim. Theor. Appl."},{"key":"1_CR13","unstructured":"Foerster, J., Nardelli, N., Farquhar, G., Torr, P.H.S., Kohli, P., Whiteson, S.: Stabilising experience replay for deep multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 1146\u20131155. PMLR, Singapore (2017)"},{"key":"1_CR14","first-page":"387","volume":"32","author":"D Silver","year":"2014","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. J. Mach. Learn. Res. 32, 387\u2013395 (2014)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Advances in Swarm Intelligence"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-26354-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,7,18]],"date-time":"2019-07-18T12:03:06Z","timestamp":1563451386000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-26354-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030263539","9783030263546"],"references-count":14,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-26354-6_1","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":"19 July 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Swarm Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chiang Mai","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","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":"26 July 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 July 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"swarm2019a","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-si.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}