{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T04:53:52Z","timestamp":1764996832653},"publisher-location":"Berlin, Heidelberg","reference-count":13,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783540779476"},{"type":"electronic","value":"9783540779490"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"DOI":"10.1007\/978-3-540-77949-0_10","type":"book-chapter","created":{"date-parts":[[2008,2,8]],"date-time":"2008-02-08T04:01:52Z","timestamp":1202443312000},"page":"129-144","source":"Crossref","is-referenced-by-count":2,"title":["Bifurcation Analysis of Reinforcement Learning Agents in the Selten\u2019s Horse Game"],"prefix":"10.1007","author":[{"given":"Alessandro","family":"Lazaric","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique","family":"Munoz de Cote","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio","family":"Dercole","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marcello","family":"Restelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"10_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jeth.1997.2319","volume":"77","author":"T. B\u00f6rgers","year":"1997","unstructured":"B\u00f6rgers, T., Sarin, R.: Learning through reinforcement and replicator dynamics. Journal of Economic Theory\u00a077(1), 1\u201314 (1997)","journal-title":"Journal of Economic Theory"},{"key":"10_CR2","unstructured":"Dercole, F., Rinaldi, S.: Analysis of Evolutionary Processes: The Adaptive Dynamics Approach and its Applications. Princeton University Press, Princeton, NJ, (forthcoming)"},{"key":"10_CR3","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1145\/779359.779362","volume":"29","author":"A. Dhooge","year":"2002","unstructured":"Dhooge, A., Govaerts, W., Kuznetsov, Y.A.: MATCONT: A MATLAB package for numerical bifurcation analysis of ODEs. ACM Trans. Math. Software\u00a029, 141\u2013164 (2002)","journal-title":"ACM Trans. Math. Software"},{"key":"10_CR4","volume-title":"Game Theory Evolving","author":"H. Gintis","year":"2000","unstructured":"Gintis, H.: Game Theory Evolving. Princeton University Press, Princeton, NJ (2000)"},{"issue":"4","key":"10_CR5","doi-asserted-by":"publisher","first-page":"863","DOI":"10.2307\/1912767","volume":"50","author":"D.M. Kreps","year":"1982","unstructured":"Kreps, D.M., Wilson, R.: Sequential equilibria. Econometrica\u00a050(4), 863\u2013894 (1982)","journal-title":"Econometrica"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Kunigami, M., Terano, T.: Connected replicator dynamics and their control in a learning multi-agent system. In: IDEAL, pp. 18\u201326 (2003)","DOI":"10.1007\/978-3-540-45080-1_3"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Kuznetsov, Y.A.: Elements of Applied Bifurcation Theory. 3rd edition (2004)","DOI":"10.1007\/978-1-4757-3978-7"},{"key":"10_CR8","first-page":"157","volume-title":"ICML","author":"M.L. Littman","year":"1994","unstructured":"Littman, M.L.: Markov games as a framework for multi-agent reinforcement learning. In: ICML, pp. 157\u2013163. New Brunswick, NJ, Morgan Kaufmann, San Francisco (1994)"},{"key":"10_CR9","volume-title":"Game Theory: Analysis of Conflict","author":"R.B. Myerson","year":"1991","unstructured":"Myerson, R.B.: Game Theory: Analysis of Conflict. Harvard University Press, Cambridge (1991)"},{"issue":"1","key":"10_CR10","doi-asserted-by":"publisher","first-page":"15206","DOI":"10.1103\/PhysRevE.67.015206","volume":"67","author":"Y. Sato","year":"2003","unstructured":"Sato, Y., Crutchfield, J.P.: Coupled replicator equations for the dynamics of learning in multiagent systems. Phys. Rev. E\u00a067(1), 15206 (2003)","journal-title":"Phys. Rev. E"},{"key":"10_CR11","volume-title":"Reinforcement Learning: An Introduction","author":"R.S. Sutton","year":"1998","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)"},{"issue":"1","key":"10_CR12","first-page":"115","volume":"12","author":"K. Tuyls","year":"2006","unstructured":"Tuyls, K., Hoen, P.J., Vanschoenwinkel, B.: An evolutionary dynamical analysis of multi-agent learning in iterated games. JAAMAS\u00a012(1), 115\u2013153 (2006)","journal-title":"JAAMAS"},{"key":"10_CR13","first-page":"279","volume":"8","author":"C.J. Watkins","year":"1992","unstructured":"Watkins, C.J., Dayan, P.: Q-learning. Machine Learning\u00a08, 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Adaptive Agents and Multi-Agent Systems III. Adaptation and Multi-Agent Learning"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-540-77949-0_10.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T10:56:46Z","timestamp":1619521006000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-540-77949-0_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[null]]},"ISBN":["9783540779476","9783540779490"],"references-count":13,"URL":"https:\/\/doi.org\/10.1007\/978-3-540-77949-0_10","relation":{},"subject":[]}}