{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T16:48:02Z","timestamp":1777826882759,"version":"3.51.4"},"publisher-location":"Cham","reference-count":13,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319783000","type":"print"},{"value":"9783319783017","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"unspecified","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":[[2018]]},"DOI":"10.1007\/978-3-319-78301-7_3","type":"book-chapter","created":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T11:05:02Z","timestamp":1525172702000},"page":"48-65","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Two-Stage Reinforcement Learning Algorithm for Quick Cooperation in Repeated Games"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4124-7264","authenticated-orcid":false,"given":"Wataru","family":"Fujita","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1735-1862","authenticated-orcid":false,"given":"Koichi","family":"Moriyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2451-1919","authenticated-orcid":false,"given":"Ken-ichi","family":"Fukui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Masayuki","family":"Numao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,4,14]]},"reference":[{"key":"3_CR1","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.jalgor.2009.04.003","volume":"64","author":"A Burkov","year":"2009","unstructured":"Burkov, A., Chaib-draa, B.: Effective learning in the presence of adaptive counterparts. J. Algorithm. 64, 127\u2013138 (2009)","journal-title":"J. Algorithm."},{"key":"3_CR2","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the 15th National Conference on Artificial Intelligence (AAAI), pp. 746\u2013752 (1998)"},{"key":"3_CR3","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1007\/s10994-010-5192-9","volume":"82","author":"JW Crandall","year":"2011","unstructured":"Crandall, J.W., Goodrich, M.A.: Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning. Mach. Learn. 82, 281\u2013314 (2011)","journal-title":"Mach. Learn."},{"key":"3_CR4","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1142\/9789814730464_0004","volume-title":"Theory and Practice of Computation","author":"W Fujita","year":"2016","unstructured":"Fujita, W., Moriyama, K., Fukui, K., Numao, M.: Learning better strategies with a combination of complementary reinforcement learning algorithms. In: Nishizaki, S., Numao, M., Caro, J.D.L., Suarez, M.T.C. (eds.) Theory and Practice of Computation, pp. 43\u201354. World Scientific, Singapore (2016)"},{"key":"3_CR5","first-page":"1039","volume":"4","author":"J Hu","year":"2003","unstructured":"Hu, J., Wellman, M.P.: Nash Q-learning for general-sum stochastic games. J. Mach. Learn. Res. 4, 1039\u20131069 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR6","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jtbi.2011.03.005","volume":"278","author":"N Masuda","year":"2011","unstructured":"Masuda, N., Nakamura, M.: Numerical analysis of a reinforcement learning model with the dynamic aspiration level in the iterated Prisoner\u2019s dilemma. J. Theor. Biol. 278, 55\u201362 (2011)","journal-title":"J. Theor. Biol."},{"key":"3_CR7","volume-title":"Game Theory","author":"A Okada","year":"2011","unstructured":"Okada, A.: Game Theory, New edn. Yuhikaku, Tokyo (2011). (in Japanese)","edition":"New"},{"key":"3_CR8","unstructured":"Rummery, G.A., Niranjan, M.: On-line Q-learning using connectionist systems. Technical report TR166, Cambridge University Engineering Department (1994)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Schembri, M., Mirolli, M., Baldassarre, G.: Evolving internal reinforcers for an intrinsically motivated reinforcement-learning robot. In: Proceedings of the 6th IEEE International Conference on Development and Learning (ICDL), pp. 282\u2013287 (2007)","DOI":"10.1109\/DEVLRN.2007.4354052"},{"key":"3_CR10","unstructured":"Stimpson, J.L., Goodrich, M.A.: Learning to cooperate in a social dilemma: a satisficing approach to bargaining. In: Proceedings of the 20th International Conference on Machine Learning (ICML), pp. 728\u2013735 (2003)"},{"key":"3_CR11","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":"3_CR12","first-page":"279","volume":"8","author":"CJCH Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8, 279\u2013292 (1992)","journal-title":"Mach. Learn."},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1109\/TSMCB.2008.920231","volume":"38","author":"MA Wiering","year":"2008","unstructured":"Wiering, M.A., van Hasselt, H.: Ensemble algorithms in reinforcement learning. IEEE Trans. Syst. Man Cybern. B 38, 930\u2013936 (2008)","journal-title":"IEEE Trans. Syst. Man Cybern. B"}],"container-title":["Lecture Notes in Computer Science","Transactions on Computational Collective Intelligence XXVIII"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-78301-7_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,5,1]],"date-time":"2018-05-01T11:07:44Z","timestamp":1525172864000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-78301-7_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783319783000","9783319783017"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-78301-7_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}