{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T14:14:40Z","timestamp":1777472080492,"version":"3.51.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2019,1,5]],"date-time":"2019-01-05T00:00:00Z","timestamp":1546646400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61473183"],"award-info":[{"award-number":["61473183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1509211"],"award-info":[{"award-number":["U1509211"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61521063"],"award-info":[{"award-number":["61521063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Fuzzy Syst."],"published-print":{"date-parts":[[2019,3]]},"DOI":"10.1007\/s40815-018-0586-0","type":"journal-article","created":{"date-parts":[[2019,1,5]],"date-time":"2019-01-05T05:42:03Z","timestamp":1546666923000},"page":"592-606","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Fuzzy Categorical Deep Reinforcement Learning of a Defensive Game for an Unmanned Surface Vessel"],"prefix":"10.1007","volume":"21","author":[{"given":"Yin","family":"Cheng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhijian","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuexin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weidong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2019,1,5]]},"reference":[{"key":"586_CR1","doi-asserted-by":"crossref","unstructured":"Manley, J.E.: Unmanned surface vehicles, 15 years of development. In: OCEANS. IEEE, pp. 1\u20134 (2008)","DOI":"10.1109\/OCEANS.2008.5289429"},{"key":"586_CR2","first-page":"1","volume":"1","author":"V Bertram","year":"2008","unstructured":"Bertram, V.: Unmanned surface vehicles-a survey. Skibsteknisk Selsk. Cph. Den. 1, 1\u201314 (2008)","journal-title":"Skibsteknisk Selsk. Cph. Den."},{"key":"586_CR3","doi-asserted-by":"crossref","unstructured":"Villa, J L., Paez, J., Quintero, C., et al.: Design and control of an unmanned surface vehicle for environmental monitoring applications. In: IEEE Colombian conference on robotics and automation (CCRA). IEEE, pp. 1\u20135 (2016)","DOI":"10.1109\/CCRA.2016.7811411"},{"issue":"5","key":"586_CR4","doi-asserted-by":"publisher","first-page":"1106","DOI":"10.1109\/TCYB.2015.2423635","volume":"46","author":"N Wang","year":"2016","unstructured":"Wang, N., Sun, J.C., Er, M.J., et al.: A novel extreme learning control framework of unmanned surface vehicles. IEEE Trans. Cybern. 46(5), 1106\u20131117 (2016)","journal-title":"IEEE Trans. Cybern."},{"key":"586_CR5","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1007\/10992388_4","volume":"8","author":"R Smierzchalski","year":"2005","unstructured":"Smierzchalski, R., Michalewicz, Z.: Path planning in dynamic environments. Innov. Robot Mobil. Control 8, 135\u2013153 (2005)","journal-title":"Innov. Robot Mobil. Control"},{"issue":"1\u20132","key":"586_CR6","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/s11071-013-0951-3","volume":"74","author":"Z Peng","year":"2013","unstructured":"Peng, Z., Wang, D., Li, T., et al.: Leaderless and leader-follower cooperative control of multiple marine surface vehicles with unknown dynamics. Nonlinear Dyn. 74(1\u20132), 95\u2013106 (2013)","journal-title":"Nonlinear Dyn."},{"key":"586_CR7","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/j.isatra.2014.12.002","volume":"56","author":"G Zhang","year":"2015","unstructured":"Zhang, G., Zhang, X.: A novel DVS guidance principle and robust adaptive path-following control for underactuated ships using low frequency gain-learning. ISA Trans. 56, 75\u201385 (2015)","journal-title":"ISA Trans."},{"issue":"4","key":"586_CR8","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1109\/JOE.2013.2280822","volume":"8","author":"G Zhang","year":"2014","unstructured":"Zhang, G., Zhang, X.: Concise robust adaptive path-following control of underactuated ships using DSC and MLP. IEEE J. Ocean. Eng. 8(4), 685\u2013694 (2014)","journal-title":"IEEE J. Ocean. Eng."},{"key":"586_CR9","doi-asserted-by":"publisher","DOI":"10.1002\/9781119994138","volume-title":"Handbook of Marine Craft Hydrodynamics and Motion Control","author":"TI Fossen","year":"2011","unstructured":"Fossen, T.I.: Handbook of Marine Craft Hydrodynamics and Motion Control. Wiley, New York (2011)"},{"key":"586_CR10","volume-title":"Ship Motion Control: Course Keeping and Roll Stabilisation Using Rudder and Fins","author":"T Perez","year":"2006","unstructured":"Perez, T.: Ship Motion Control: Course Keeping and Roll Stabilisation Using Rudder and Fins. Springer, Berlin (2006)"},{"issue":"1","key":"586_CR11","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1109\/MCS.2016.2621461","volume":"37","author":"KG Vamvoudakis","year":"2017","unstructured":"Vamvoudakis, K.G., Modares, H., Kiumarsi, B., et al.: Game theory-based control system algorithms with real-time reinforcement learning: how to solve multiplayer games online. IEEE Control Syst. 37(1), 33\u201352 (2017)","journal-title":"IEEE Control Syst."},{"key":"586_CR12","doi-asserted-by":"crossref","DOI":"10.1201\/b21050","volume-title":"Introducing Game Theory and Its Applications","author":"E Mendelson","year":"2016","unstructured":"Mendelson, E.: Introducing Game Theory and Its Applications. CRC Press, Boca Raton (2016)"},{"issue":"2","key":"586_CR13","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1109\/TNNLS.2015.2464080","volume":"27","author":"Q Wei","year":"2016","unstructured":"Wei, Q., Song, R., Yan, P.: Data-driven zero-sum neuro-optimal control for a class of continuous-time unknown nonlinear systems with disturbance using ADP. IEEE Trans. Neural Netw. Learn. Syst. 27(2), 444\u2013458 (2016)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"12","key":"586_CR14","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1287\/mnsc.1040.0270","volume":"50_supplement","author":"JC Harsanyi","year":"2004","unstructured":"Harsanyi, J.C.: Games with incomplete information played by Bayesian players: part I. The basic model. Manag. Sci 50_supplement(12), 1804\u20131817 (2004)","journal-title":"Manag. Sci"},{"key":"586_CR15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511794216","volume-title":"Game Theory","author":"Michael Maschler","year":"2013","unstructured":"Maschler, Michael, Solan, Eilon, Zamir, Shmuel: Game Theory. Cambridge University Press, Cambridge (2013)"},{"key":"586_CR16","unstructured":"Mei, S., Wang, Y., Sun, Z.: Robust economic dispatch considering renewable generation. In: 2011 IEEE PES Innovative Smart Grid Technologies Asia (ISGT). IEEE, pp. 1\u20135 (2011)"},{"key":"586_CR17","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":"586_CR18","doi-asserted-by":"crossref","DOI":"10.1201\/b18188","volume-title":"Reinforcement Learning: Modern Machine Learning Approaches","author":"Sugiyama M Statistical","year":"2015","unstructured":"Statistical, Sugiyama M.: Reinforcement Learning: Modern Machine Learning Approaches. CRC Press, Boca Raton (2015)"},{"issue":"2","key":"586_CR19","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TNNLS.2014.2371046","volume":"26","author":"D Zhao","year":"2015","unstructured":"Zhao, D., Zhu, Y.M.E.C.: A near-optimal online reinforcement learning algorithm for continuous deterministic systems. IEEE Trans. Neural Netw. Learn. Syst. 26(2), 346\u2013356 (2015)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"586_CR20","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TNNLS.2016.2522401","volume":"28","author":"Y Deng","year":"2017","unstructured":"Deng, Y., Bao, F., Kong, Y., et al.: Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans. Neural Netw. Learn. Syst. 28(3), 653\u2013664 (2017)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"586_CR21","doi-asserted-by":"publisher","DOI":"10.1512\/iumj.1957.6.56038","volume-title":"A Markovian Decision Process","author":"R Bellman","year":"1957","unstructured":"Bellman, R.: A Markovian Decision Process. RAND Corp, Santa Monica (1957)"},{"key":"586_CR22","unstructured":"Li, Y.: Deep reinforcement learning: an overview. arXiv preprint arXiv:1701.07274 (2017)"},{"key":"586_CR23","unstructured":"Mnih, V., Badia, A P., Mirza, M., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"586_CR24","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: The International Conference on Machine Learning (ICML) (2014)"},{"issue":"3\u20134","key":"586_CR25","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":"7540","key":"586_CR26","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., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"586_CR27","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F. (ed.) Advances in Neural Information Processing Systems, pp. 1097\u20131105. Curran Associates, New York, NY (2012)"},{"key":"586_CR28","unstructured":"Bellemare, M. G., Dabney, W., Munos, R.: A distributional perspective on reinforcement learning. In: International Conference on Machine Learning, pp. 449\u2013458 (2017)"},{"key":"586_CR29","doi-asserted-by":"publisher","unstructured":"Caspi, I., Leibovich, G., Novik, G., Endrawis, S.: Reinforcement Learning Coach (2017). https:\/\/doi.org\/10.5281\/zenodo.1134899","DOI":"10.5281\/zenodo.1134899"}],"container-title":["International Journal of Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s40815-018-0586-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s40815-018-0586-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s40815-018-0586-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,21]],"date-time":"2020-11-21T19:34:59Z","timestamp":1605987299000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s40815-018-0586-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,5]]},"references-count":29,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,3]]}},"alternative-id":["586"],"URL":"https:\/\/doi.org\/10.1007\/s40815-018-0586-0","relation":{},"ISSN":["1562-2479","2199-3211"],"issn-type":[{"value":"1562-2479","type":"print"},{"value":"2199-3211","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,5]]},"assertion":[{"value":"8 February 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 October 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 November 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 January 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}