{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T10:21:28Z","timestamp":1725704488800},"publisher-location":"Berlin, Heidelberg","reference-count":21,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642347986"},{"type":"electronic","value":"9783642347993"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2012]]},"DOI":"10.1007\/978-3-642-34799-3_10","type":"book-chapter","created":{"date-parts":[[2012,10,25]],"date-time":"2012-10-25T14:30:20Z","timestamp":1351175420000},"page":"145-159","source":"Crossref","is-referenced-by-count":0,"title":["Multi-agent Learning and the Reinforcement Gradient"],"prefix":"10.1007","author":[{"given":"Michael","family":"Kaisers","sequence":"first","affiliation":[]},{"given":"Daan","family":"Bloembergen","sequence":"additional","affiliation":[]},{"given":"Karl","family":"Tuyls","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"issue":"1","key":"10_CR1","doi-asserted-by":"crossref","first-page":"521","DOI":"10.1613\/jair.2628","volume":"33","author":"S. Abdallah","year":"2008","unstructured":"Abdallah, S., Lesser, V.: A multiagent reinforcement learning algorithm with non-linear dynamics. Journal of Artificial Intelligence Research\u00a033(1), 521\u2013549 (2008)","journal-title":"Journal of Artificial Intelligence Research"},{"doi-asserted-by":"crossref","unstructured":"Blum, A., Mansour, Y.: Learning, regret minimization and equilibria. Cambridge University Press (2007)","key":"10_CR2","DOI":"10.1145\/1324249.1324252"},{"doi-asserted-by":"crossref","unstructured":"B\u00f6rgers, T., Sarin, R.: Learning through reinforcement and replicator dynamics. Journal of Economic Theory 77(1) (November 1997)","key":"10_CR3","DOI":"10.1006\/jeth.1997.2319"},{"key":"10_CR4","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M. Bowling","year":"2002","unstructured":"Bowling, M., Veloso, M.: Multiagent learning using a variable learning rate. Artificial Intelligence\u00a0136, 215\u2013250 (2002)","journal-title":"Artificial Intelligence"},{"issue":"2","key":"10_CR5","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 Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews\u00a038(2), 156\u2013172 (2008)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews"},{"doi-asserted-by":"crossref","unstructured":"Crandall, J.W., Ahmed, A., Goodrich, M.A.: Learning in repeated games with minimal information: The effects of learning bias. In: Twenty-Fifth AAAI Conference on Artificial Intelligence (2011)","key":"10_CR6","DOI":"10.1609\/aaai.v25i1.7871"},{"issue":"2","key":"10_CR7","doi-asserted-by":"publisher","first-page":"239","DOI":"10.2307\/1882186","volume":"87","author":"J.G. Cross","year":"1973","unstructured":"Cross, J.G.: A stochastic learning model of economic behavior. The Quarterly Journal of Economics\u00a087(2), 239 (1973)","journal-title":"The Quarterly Journal of Economics"},{"unstructured":"Gibbons, R.: A Primer in Game Theory. Pearson Education (1992)","key":"10_CR8"},{"key":"10_CR9","doi-asserted-by":"crossref","DOI":"10.2307\/j.ctvcm4gjh","volume-title":"Game Theory Evolving","author":"H. Gintis","year":"2009","unstructured":"Gintis, H.: Game Theory Evolving, 2nd edn. University Press, Princeton (2009)","edition":"2"},{"unstructured":"Hofbauer, J., Sigmund, K.: Evolutionary Games and Population Dynamics. Cambridge University Press (2002)","key":"10_CR10"},{"unstructured":"Kaisers, M., Tuyls, K.: Frequency adjusted multi-agent Q-learning. In: Proc. of 9th Intl. Conf. on Autonomous Agents and Multiagent Systems (AAMAS 2010), May 10-14, pp. 309\u2013315 (2010)","key":"10_CR11"},{"unstructured":"Kaisers, M., Tuyls, K.: Faq-learning in matrix games: Demonstrating convergence near nash equilibria, and bifurcation of attractors in the battle of sexes. In: Proceedings of the Workshop on Interactive Decision Theory and Game Theory (2011)","key":"10_CR12"},{"key":"10_CR13","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1007\/978-3-642-15883-4_6","volume-title":"Machine Learning and Knowledge Discovery in Databases","author":"T. Klos","year":"2010","unstructured":"Klos, T., van Ahee, G.J., Tuyls, K.: Evolutionary Dynamics of Regret Minimization. In: Balc\u00e1zar, J.L., Bonchi, F., Gionis, A., Sebag, M. (eds.) ECML PKDD 2010, Part II. LNCS, vol.\u00a06322, pp. 82\u201396. Springer, Heidelberg (2010)"},{"issue":"2","key":"10_CR14","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/246015a0","volume":"246","author":"J. Maynard Smith","year":"1973","unstructured":"Maynard Smith, J., Price, G.R.: The logic of animal conflict. Nature\u00a0246(2), 15\u201318 (1973)","journal-title":"Nature"},{"issue":"4","key":"10_CR15","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1109\/TSMC.1974.5408453","volume":"4","author":"K.S. Narendra","year":"1974","unstructured":"Narendra, K.S., Thathachar, M.A.L.: Learning automata - a survey. IEEE Transactions on Systems, Man, and Cybernetics\u00a04(4), 323\u2013334 (1974)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics"},{"key":"10_CR16","volume-title":"Population Games and Evolutionary Dynamics","author":"W.H. Sandholm","year":"2010","unstructured":"Sandholm, W.H.: Population Games and Evolutionary Dynamics. The MIT Press, Cambridge (2010)"},{"unstructured":"Singh, S., Kearns, M., Mansour, Y.: Nash convergence of gradient dynamics in general-sum games. In: Proc. of the 16th Conference on Uncertainty in Artificial Intelligence, pp. 541\u2013548 (2000)","key":"10_CR17"},{"key":"10_CR18","volume-title":"Reinforcement Learning: An introduction","author":"R. Sutton","year":"1998","unstructured":"Sutton, R., Barto, A.: Reinforcement Learning: An introduction. MIT Press, Cambridge (1998)"},{"issue":"6","key":"10_CR19","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1109\/TSMCB.2002.1049606","volume":"32","author":"M.A.L. Thathachar","year":"2002","unstructured":"Thathachar, M.A.L., Sastry, P.S.: Varieties of learning automata: An overview. IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics\u00a032(6), 711\u2013722 (2002)","journal-title":"IEEE Transactions on Systems, Man, and Cybernetics - Part B: Cybernetics"},{"key":"10_CR20","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s10458-005-3783-9","volume":"12","author":"K. Tuyls","year":"2006","unstructured":"Tuyls, K., Jan\u2019t Hoen, P., Vanschoenwinkel, B.: An evolutionary dynamical analysis of multi-agent learning in iterated games. Autonomous Agents and Multi-Agent Systems\u00a012, 115\u2013153 (2006)","journal-title":"Autonomous Agents and Multi-Agent Systems"},{"issue":"3","key":"10_CR21","first-page":"279","volume":"8","author":"C.J.C.H. Watkins","year":"1992","unstructured":"Watkins, C.J.C.H., Dayan, P.: Q-learning. Machine Learning\u00a08(3), 279\u2013292 (1992)","journal-title":"Machine Learning"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-34799-3_10.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,26]],"date-time":"2023-06-26T10:57:53Z","timestamp":1687777073000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-34799-3_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2012]]},"ISBN":["9783642347986","9783642347993"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-34799-3_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2012]]}}}