{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:07:47Z","timestamp":1743142067427,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030328122"},{"type":"electronic","value":"9783030328139"}],"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\/978-3-030-32813-9_17","type":"book-chapter","created":{"date-parts":[[2019,10,15]],"date-time":"2019-10-15T15:01:33Z","timestamp":1571151693000},"page":"202-214","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-USVs Coordinated Detection in Marine Environment with Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Ruiying","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kai","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haichang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,10,8]]},"reference":[{"issue":"12","key":"17_CR1","doi-asserted-by":"publisher","first-page":"2032","DOI":"10.14778\/2367502.2367572","volume":"5","author":"A Labrinidis","year":"2012","unstructured":"Labrinidis, A., Jagadish, H.V.: Challenges and opportunities with big data. Proc. VLDB Endow. 5(12), 2032\u20132033 (2012)","journal-title":"Proc. VLDB Endow."},{"issue":"1","key":"17_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00530-015-0482-5","volume":"22","author":"S Jitao","year":"2016","unstructured":"Jitao, S., Gao, Y., Bingkun, B., Snoek, C., Dai, Q.: Recent advances in social multimedia big data mining and applications. Multimed. Syst. 22(1), 1\u20133 (2016)","journal-title":"Multimed. Syst."},{"key":"17_CR3","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139924801","volume-title":"Mining of Massive Datasets","author":"J Leskovec","year":"2014","unstructured":"Leskovec, J., Rajaraman, A., Ullman, J.D.: Mining of Massive Datasets, 2nd edn. Cambridge University Press, Cambridge (2014)","edition":"2"},{"key":"17_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1998.712192","volume-title":"Introduction to Reinforcement Learning","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Introduction to Reinforcement Learning. MIT Press, Cambridge (1998)"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"17_CR6","unstructured":"Schmidhuber, J.: A general method for multi-agent reinforcement learning in unrestricted environments. In: Adaptation, Coevolution and Learning in Multiagent Systems: Papers from the 1996 AAAI Spring Symposium, pp. 84\u201387 (1996)"},{"issue":"2","key":"17_CR7","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 Appl. Rev. 38(2), 156\u2013172 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C Appl. Rev."},{"issue":"1","key":"17_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0269888912000057","volume":"27","author":"L Matignon","year":"2012","unstructured":"Matignon, L., Laurent, G.J., Le Fort-Piat, N.: 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":"3","key":"17_CR9","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s10458-005-2631-2","volume":"11","author":"L Panait","year":"2005","unstructured":"Panait, L., Luke, S.: Cooperative multi-agent learning: the state of the art. Auton. Agents Multi-Agent Syst. 11(3), 387\u2013434 (2005)","journal-title":"Auton. Agents Multi-Agent Syst."},{"issue":"4","key":"17_CR10","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1137\/S0363012901385691","volume":"42","author":"VR Konda","year":"2003","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Onactor-critic algorithms. SIAM J. Control Optim. 42(4), 1143\u20131166 (2003)","journal-title":"SIAM J. Control Optim."},{"issue":"6","key":"17_CR11","doi-asserted-by":"publisher","first-page":"1291","DOI":"10.1109\/TSMCC.2012.2218595","volume":"42","author":"I Grondman","year":"2012","unstructured":"Grondman, I., Busoniu, L., Lopes, G.A.D., et al.: A survey of actor-critic reinforcement learning: standard and natural policy gradients. IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.) 42(6), 1291\u20131307 (2012)","journal-title":"IEEE Trans. Syst. Man Cybern. Part C (Appl. Rev.)"},{"issue":"3\u20134","key":"17_CR12","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R.J.: Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8(3\u20134), 229\u2013256 (1992)","journal-title":"Mach. Learn."},{"key":"17_CR13","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"17_CR14","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"17_CR15","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"key":"17_CR16","unstructured":"Zhang, C., Lesser, V.: Coordinating multi-agent reinforcement learning with limited communication. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-agent Systems, pp. 1101\u20131108. International Foundation for Autonomous Agents and Multiagent Systems (2013)"},{"key":"17_CR17","unstructured":"Foerster, J., Assael, I.A., Freitas, N., Whiteson, S.: Learning to communicate with deep multi-agent reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 2137\u20132145 (2016)"},{"key":"17_CR18","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: Proceedings of the 31st International Conference on Machine Learning, pp. 387\u2013395 (2014)"},{"issue":"7540","key":"17_CR19","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529 (2015)","journal-title":"Nature"},{"key":"17_CR20","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, O.P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6379\u20136390 (2017)"},{"issue":"8","key":"17_CR21","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.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"issue":"4","key":"17_CR22","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1002\/j.2161-4296.1996.tb01929.x","volume":"43","author":"T Vaneck","year":"1996","unstructured":"Vaneck, T., Manley, J., Rodriguez, C., Schmidt, M.: Automated bathymetry using an autonomous surface craft navigation. J. Inst. Navig. 43(4), 407\u2013419 (1996)","journal-title":"J. Inst. Navig."},{"key":"17_CR23","unstructured":"Bertram, V.: Unmanned surface vehicles - a survey. Skibsteknisk Selskab (2008)"},{"key":"17_CR24","unstructured":"Enderle, B., Yanagihara, T., Suemori, M., Imai, H., Sato, A.: Recent developments in a total unmanned integration system. In: AUVSI Unmanned Systems Conference, Anaheim (2004)"},{"key":"17_CR25","doi-asserted-by":"publisher","first-page":"19","DOI":"10.5875\/ausmt.v1i2.122","volume":"1","author":"W Yang","year":"2011","unstructured":"Yang, W., Chen, C., Hsu, C., Tseng, C., Yang, W.: Multifunctional inshore survey platform with unmanned surface vehicles. Int. J. Autom. Smart Technol. 1, 19\u201325 (2011)","journal-title":"Int. J. Autom. Smart Technol."},{"issue":"3","key":"17_CR26","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1109\/MRA.2005.1511873","volume":"12","author":"M Caccia","year":"2005","unstructured":"Caccia, M., et al.: Sampling sea surfaces with SESAMO: an autonomous craft for the study of sea-air interactions. Robot. Autom. Mag. 12(3), 95\u2013105 (2005)","journal-title":"Robot. Autom. Mag."},{"issue":"7553","key":"17_CR27","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521(7553), 436\u2013444 (2015)","journal-title":"Nature"},{"key":"17_CR28","unstructured":"Lowe, R., Wu, Y., Tamar, A., Harb, J., Abbeel, P., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. In: Advances in Neural Information Processing Systems, pp. 6382\u20136393 (2017)"},{"key":"17_CR29","unstructured":"Boutilier, C.: Learning conventions in multiagent stochastic domains using likelihood estimates. In: Proceedings of the Twelfth International Conference on Uncertainty in Artificial Intelligence, pp. 106\u2013114 (1996)"},{"key":"17_CR30","unstructured":"Nielsen, M.A.: Neural Networks and Deep Learning. Determination Press (2015)"},{"key":"17_CR31","volume-title":"Dynamic Programming and Optimal Control","author":"DP Bertsekas","year":"2005","unstructured":"Bertsekas, D.P.: Dynamic Programming and Optimal Control. Athena Scientific, Belmont (2005)"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-32813-9_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,19]],"date-time":"2021-02-19T03:57:51Z","timestamp":1613707071000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-32813-9_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019]]},"ISBN":["9783030328122","9783030328139"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-32813-9_17","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":"8 October 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Seattle, WA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2018","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 December 2018","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 December 2018","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2018","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/prof.ict.ac.cn\/Bench18\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CyberDhair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"51","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}