{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T14:51:19Z","timestamp":1725979879733},"publisher-location":"Cham","reference-count":11,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319920306"},{"type":"electronic","value":"9783319920313"}],"license":[{"start":{"date-parts":[[2018,5,31]],"date-time":"2018-05-31T00:00:00Z","timestamp":1527724800000},"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":[[2019]]},"DOI":"10.1007\/978-3-319-92031-3_2","type":"book-chapter","created":{"date-parts":[[2018,5,30]],"date-time":"2018-05-30T15:04:57Z","timestamp":1527692697000},"page":"13-22","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Evolution Direction of Reward Appraisal in Reinforcement Learning Agents"],"prefix":"10.1007","author":[{"given":"Masaya","family":"Miyawaki","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Koichi","family":"Moriyama","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsuko","family":"Mutoh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tohgoroh","family":"Matsui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobuhiro","family":"Inuzuka","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,5,31]]},"reference":[{"key":"2_CR1","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1016\/S0896-6273(02)00755-9","volume":"35","author":"JK Rilling","year":"2002","unstructured":"Rilling, J.K., Gutman, D.A., Zeh, T.R., Pagnoni, G., Berns, G.S., Kilts, C.D.: A neural basis for social cooperation. Neuron 35, 395\u2013405 (2002)","journal-title":"Neuron"},{"key":"2_CR2","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/0303-2647(95)01551-5","volume":"37","author":"TW Sandholm","year":"1996","unstructured":"Sandholm, T.W., Crites, R.H.: Multiagent reinforcement learning in the Iterated Prisoner\u2019s Dilemma. BioSystems 37, 147\u2013166 (1996)","journal-title":"BioSystems"},{"issue":"3","key":"2_CR3","doi-asserted-by":"crossref","first-page":"233","DOI":"10.3233\/WIA-2009-0165","volume":"7","author":"K Moriyama","year":"2009","unstructured":"Moriyama, K.: Utility based Q-learning to facilitate cooperation in Prisoner\u2019s Dilemma games. Web Intell. Agent Syst. 7(3), 233\u2013242 (2009)","journal-title":"Web Intell. Agent Syst."},{"key":"2_CR4","unstructured":"Moriyama, K., Kurihara, S., Numao, M.: Evolving subjective utilities: Prisoner\u2019s Dilemma game examples. In: Proceedings of the 10th International Conference on Autonomous Agents and Multi-Agent Systems (AAMAS), pp. 233\u2013240 (2011)"},{"key":"2_CR5","volume-title":"The Evolution of Cooperation","author":"R Axelrod","year":"1984","unstructured":"Axelrod, R.: The Evolution of Cooperation. Basic Books, New York (1984)"},{"key":"2_CR6","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":"2_CR7","volume-title":"Genetic Algorithms in Search, Optimization and Machine Learning","author":"DE Goldberg","year":"1989","unstructured":"Goldberg, D.E.: Genetic Algorithms in Search, Optimization and Machine Learning. Addison-Wesley, Reading (1989)"},{"key":"2_CR8","first-page":"32","volume-title":"Genetic Algorithms and Simulated Annealing","author":"R Axelrod","year":"1987","unstructured":"Axelrod, R.: The evolution of strategies in the Iterated Prisoner\u2019s Dilemma. In: Davis, L. (ed.) Genetic Algorithms and Simulated Annealing, pp. 32\u201341. Pitman\/Morgan Kaufmann, London\/Los Altos (1987)"},{"key":"2_CR9","doi-asserted-by":"publisher","first-page":"1560","DOI":"10.1126\/science.1133755","volume":"314","author":"MA Nowak","year":"2006","unstructured":"Nowak, M.A.: Five rules for the evolution of cooperation. Science 314, 1560\u20131563 (2006)","journal-title":"Science"},{"key":"2_CR10","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1109\/TAMD.2010.2051031","volume":"2","author":"S Singh","year":"2010","unstructured":"Singh, S., Lewis, R.L., Barto, A.G., Sorg, J.: Intrinsically motivated reinforcement learning: an evolutionary perspective. IEEE Trans. Auton. Ment. Dev. 2, 70\u201382 (2010)","journal-title":"IEEE Trans. Auton. Ment. Dev."},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Vassiliades, V., Christodoulou, C.: Multiagent reinforcement learning in the Iterated Prisoner\u2019s Dilemma: fast cooperation through evolved payoffs. In: Proceedings of the 2010 International Joint Conference on Neural Networks (IJCNN) (2010)","DOI":"10.1109\/IJCNN.2010.5596937"}],"container-title":["Smart Innovation, Systems and Technologies","Agents and Multi-Agent Systems: Technologies and Applications 2018"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-92031-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,2]],"date-time":"2020-11-02T21:41:54Z","timestamp":1604353314000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-92031-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,31]]},"ISBN":["9783319920306","9783319920313"],"references-count":11,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-92031-3_2","relation":{},"ISSN":["2190-3018","2190-3026"],"issn-type":[{"type":"print","value":"2190-3018"},{"type":"electronic","value":"2190-3026"}],"subject":[],"published":{"date-parts":[[2018,5,31]]}}}