{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T06:09:49Z","timestamp":1775282989251,"version":"3.50.1"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030017125","type":"print"},{"value":"9783030017132","type":"electronic"}],"license":[{"start":{"date-parts":[[2018,1,1]],"date-time":"2018-01-01T00:00:00Z","timestamp":1514764800000},"content-version":"tdm","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\/978-3-030-01713-2_1","type":"book-chapter","created":{"date-parts":[[2018,11,23]],"date-time":"2018-11-23T14:22:06Z","timestamp":1542982926000},"page":"3-21","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Multiagent Learning Paradigms"],"prefix":"10.1007","author":[{"given":"K.","family":"Tuyls","sequence":"first","affiliation":[]},{"given":"P.","family":"Stone","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2018,10,14]]},"reference":[{"key":"1_CR1","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.artint.2018.01.002","volume":"258","author":"SV Albrecht","year":"2018","unstructured":"Albrecht, S.V., Stone, P.: Autonomous agents modelling other agents: a comprehensive survey and open problems. Artif. Intell. 258, 66\u201395 (2018)","journal-title":"Artif. Intell."},{"issue":"35","key":"1_CR2","doi-asserted-by":"publisher","first-page":"4661","DOI":"10.1016\/j.tcs.2011.05.001","volume":"412","author":"Y Altshuler","year":"2011","unstructured":"Altshuler, Y., Bruckstein, A.M.: Static and expanding grid coverage with ant robots: complexity results. Theor. Comput. Sci. 412(35), 4661\u20134674 (2011)","journal-title":"Theor. Comput. Sci."},{"key":"1_CR3","doi-asserted-by":"publisher","first-page":"797","DOI":"10.2307\/2118364","volume":"107","author":"A Banerjee","year":"1992","unstructured":"Banerjee, A.: A simple model of herd behavior. Q. J. Econ. 107, 797\u2013817 (1992)","journal-title":"Q. J. Econ."},{"key":"1_CR4","unstructured":"Barrett, S., Stone, P., Kraus, S.: Empirical evaluation of ad hoc teamwork in the pursuit domain. In: 10th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), Taipei, Taiwan, 2\u20136 May, 2011, vol. 1\u20133, pp. 567\u2013574 (2011)"},{"key":"1_CR5","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1613\/jair.4818","volume":"53","author":"D Bloembergen","year":"2015","unstructured":"Bloembergen, D., Tuyls, K., Hennes, D., Kaisers, M.: Evolutionary dynamics of multi-agent learning: a survey. J. Artif. Intell. Res. 53, 659\u2013697 (2015)","journal-title":"J. Artif. Intell. Res."},{"key":"1_CR6","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1007\/978-3-319-22416-9_8","volume-title":"Towards Autonomous Robotic Systems","author":"Bastian Broecker","year":"2015","unstructured":"Broecker, B., Caliskanelli, I., Tuyls, K., Sklar, E.I., Hennes, D.: Hybrid insect-inspired multi-robot coverage in complex environments. In: Proceedings of the Towards Autonomous Robotic Systems - 16th Annual Conference, TAROS 2015, Liverpool, UK, 8\u201310 September 2015, pp. 56\u201368 (2015)"},{"key":"1_CR7","unstructured":"Claus, C., Boutilier, C.: The dynamics of reinforcement learning in cooperative multiagent systems. In: Proceedings of the Fifteenth National Conference on Artificial Intelligence and Tenth Innovative Applications of Artificial Intelligence Conference, AAAI 98, IAAI 98, Madison, Wisconsin, USA, 26\u201330 July, 1998, pp. 746\u2013752 (1998)"},{"key":"1_CR8","unstructured":"Colorni, A., Dorigo, M., Maniezzo, V.: Distributed optimization by ant colonies. In: Varela, F.J., Bourgine, P. (eds.) Towards a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life, pp. 134\u2013142. MIT Press, Cambridge (1992)"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Dorigo, M., St\u00fctzle, T.: Ant Colony Optimization. MIT Press, Cambridge (2004)","DOI":"10.7551\/mitpress\/1290.001.0001"},{"issue":"1","key":"1_CR10","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1162\/evco.1993.1.1.77","volume":"1","author":"DB Fogel","year":"1993","unstructured":"Fogel, D.B.: Evolving behaviors in the iterated prisoner\u2019s dilemma. Evol. Comput. 1(1), 77\u201397 (1993)","journal-title":"Evol. Comput."},{"key":"1_CR11","unstructured":"Fogel, D.B.: Evolutionary computation - toward a new philosophy of machine intelligence. IEEE (1995)"},{"key":"1_CR12","volume-title":"Social Learning: Psychologicand Biological Perspectives","author":"B Galef","year":"1988","unstructured":"Galef, B.: Imitation in animals: history, definition, and interpretation of data from the psychological laboratory. In: Zentall, T., Galef, B. (eds.) Social Learning: Psychologicand Biological Perspectives. Lawrence Erlbaum Associates, Hillsdale (1988)"},{"key":"1_CR13","unstructured":"Gatti, N., Restelli, M.: Sequence-form and evolutionary dynamics: realization equivalence to agent form and logit dynamics. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, Phoenix, Arizona, USA, 12\u201317 February 2016, pp. 509\u2013515 (2016)"},{"key":"1_CR14","first-page":"110","volume-title":"Lecture Notes in Computer Science","author":"Katie Genter","year":"2014","unstructured":"Genter, K.L., Stone, P.: Influencing a flock via ad hoc teamwork. In: Proceedings of the Swarm Intelligence - 9th International Conference, ANTS 2014, Brussels, Belgium, 10\u201312 September 2014, pp. 110\u2013121 (2014)"},{"key":"1_CR15","volume-title":"Game Theory Evolving","author":"H Gintis","year":"2009","unstructured":"Gintis, H.: Game Theory Evolving, 2nd edn. University Press, Princeton (2009)","edition":"2"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Hofbauer, J., Sigmund, K.: Evolutionary Games and Population Dynamics. Cambridge University Press, Cambridge (1998)","DOI":"10.1017\/CBO9781139173179"},{"key":"1_CR17","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":"1_CR18","unstructured":"Kaisers, M., Tuyls, K.: Frequency adjusted multi-agent q-learning. In: 9th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2010), Toronto, Canada, 10\u201314 May, 2010, vol. 1\u20133, pp. 309\u2013316 (2010)"},{"key":"1_CR19","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","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. LNCS (LNAI), vol. 6322, pp. 82\u201396. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15883-4_6"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Knudson, M., Tumer, K.: Policy transfer in mobile robots using neuro-evolutionary navigation. In: Genetic and Evolutionary Computation Conference, GECCO 2012, Philadelphia, PA, USA, 7\u201311 July, 2012, Companion Material Proceedings, pp. 1411\u20131412 (2012)","DOI":"10.1145\/2330784.2330958"},{"key":"1_CR21","volume-title":"Perspectives in Ethology","author":"K Laland","year":"1993","unstructured":"Laland, K., Richerson, P., Boyd, R.: Animal social learning: toward a new theoretical approach. In: Klopfer, P., Bateson, P., Thomson, N. (eds.) Perspectives in Ethology. Plenum Press, New York (1993)"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Lanctot, M.: Further developments of extensive-form replicator dynamics using the sequence-form representation. In: International Conference on Autonomous Agents and Multi-Agent Systems, AAMAS 2014, Paris, France, 5\u20139 May, 2014, pp. 1257\u20131264 (2014)","DOI":"10.65109\/CHTP1993"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Littman, M.: Markov games as a framework for multi-agent reinforcement learning. In: Proceedings of the Eleventh International Conference on Machine Learning, pp. 157\u2013163 (1994)","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"1_CR24","unstructured":"Manderick, B., Spiessens, P.: Fine-grained parallel genetic algorithms. In: Proceedings of the 3rd International Conference on Genetic Algorithms, George Mason University, Fairfax, Virginia, USA, pp. 428\u2013433, June 1989"},{"issue":"2","key":"1_CR25","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 246(2), 15\u201318 (1973)","journal-title":"Nature"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Mitchell, M.: An Introduction to Genetic Algorithms. MIT Press, Cambridge (1998)","DOI":"10.7551\/mitpress\/3927.001.0001"},{"key":"1_CR27","series-title":"McGraw Hill Series in Computer Science","volume-title":"Machine Learning","author":"TM Mitchell","year":"1997","unstructured":"Mitchell, T.M.: Machine Learning. McGraw Hill Series in Computer Science. McGraw-Hill, New York (1997)"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Palmer, G., Tuyls, K., Bloembergen, D., Savani, R.: Lenient multi-agent deep reinforcement learning. Accepted for AAMAS 2018 (2018)","DOI":"10.65109\/QDCV6054"},{"key":"1_CR29","first-page":"423","volume":"9","author":"L Panait","year":"2008","unstructured":"Panait, L., Tuyls, K., Luke, S.: Theoretical advantages of lenient learners: an evolutionary game theoretic perspective. J. Mach. Learn. Res. 9, 423\u2013457 (2008)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"1_CR30","doi-asserted-by":"publisher","first-page":"353","DOI":"10.1287\/ijoc.1090.0353","volume":"22","author":"D Pardoe","year":"2010","unstructured":"Pardoe, D., Stone, P., Saar-Tsechansky, M., Keskin, T., Tomak, K.: Adaptive auction mechanism design and the incorporation of prior knowledge. INFORMS J. Comput. 22(3), 353\u2013370 (2010)","journal-title":"INFORMS J. Comput."},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Pardoe, D., Stone, P., Saar-Tsechansky, M., Tomak, K.: Adaptive mechanism design: a metalearning approach. In: Proceedings of the 8th International Conference on Electronic Commerce: The new e-commerce - Innovations for Conquering Current Barriers, Obstacles and Limitations to Conducting Successful Business on the Internet, 2006, Fredericton, New Brunswick, Canada, 13\u201316 August, 2006, pp. 92\u2013102 (2006)","DOI":"10.1145\/1151454.1151480"},{"issue":"4","key":"1_CR32","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1162\/artl.1995.2.4.355","volume":"2","author":"J Paredis","year":"1995","unstructured":"Paredis, J.: Coevolutionary computation. Artif. Life 2(4), 355\u2013375 (1995)","journal-title":"Artif. Life"},{"key":"1_CR33","doi-asserted-by":"crossref","unstructured":"Parkes, D.C.: On Learnable Mechanism Design, p. 107\u2013131. Springer-Verlag (2004)","DOI":"10.1007\/978-1-4419-8909-3_3"},{"issue":"7","key":"1_CR34","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1016\/j.artint.2007.02.004","volume":"171","author":"T Sandholm","year":"2007","unstructured":"Sandholm, T.: Perspectives on multiagent learning. Artif. Intell. 171(7), 382\u2013391 (2007)","journal-title":"Artif. Intell."},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Saravanan, N., Fogel, D.B.: Evolving neurocontrollers using evolutionary programming. In: Proceedings of the First IEEE Conference on Evolutionary Computation, IEEE World Congress on Computational Intelligence, Orlando, Florida, USA, 27\u201329 June, 1994, pp. 217\u2013222 (1994)","DOI":"10.1109\/ICEC.1994.350013"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Shoham, Y., Leyton-Brown, K.: Multiagent Systems - Algorithmic, Game-Theoretic, and Logical Foundations. Cambridge University Press, Cambridge (2009)","DOI":"10.1017\/CBO9780511811654"},{"issue":"7","key":"1_CR37","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1016\/j.artint.2006.02.006","volume":"171","author":"Y Shoham","year":"2007","unstructured":"Shoham, Y., Powers, R., Grenager, T.: If multi-agent learning is the answer, what is the question? Artif. Intell. 171(7), 365\u2013377 (2007)","journal-title":"Artif. Intell."},{"issue":"7","key":"1_CR38","doi-asserted-by":"publisher","first-page":"402","DOI":"10.1016\/j.artint.2006.12.005","volume":"171","author":"P Stone","year":"2007","unstructured":"Stone, P.: Multiagent learning is not the answer. it is the question. Artif. Intell. 171(7), 402\u2013405 (2007)","journal-title":"Artif. Intell."},{"issue":"3","key":"1_CR39","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1023\/A:1008942012299","volume":"8","author":"P Stone","year":"2000","unstructured":"Stone, P., Veloso, M.M.: Multiagent systems: a survey from a machine learning perspective. Auton. Robots 8(3), 345\u2013383 (2000)","journal-title":"Auton. Robots"},{"issue":"1","key":"1_CR40","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s10458-005-3783-9","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. Auton. Agents Multi-Agent Syst. 12(1), 115\u2013153 (2006)","journal-title":"Auton. Agents Multi-Agent Syst."},{"issue":"7","key":"1_CR41","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1016\/j.artint.2007.01.004","volume":"171","author":"K Tuyls","year":"2007","unstructured":"Tuyls, K., Parsons, S.: What evolutionary game theory tells us about multiagent learning. Artif. Intell. 171(7), 406\u2013416 (2007)","journal-title":"Artif. Intell."},{"issue":"1","key":"1_CR42","doi-asserted-by":"publisher","first-page":"1015","DOI":"10.1038\/s41598-018-19194-4","volume":"8","author":"K Tuyls","year":"2018","unstructured":"Tuyls, K., P\u00e9rolat, J., Lanctot, M., Ostrovski, G., Savani, R., Leibo, J.Z., Ord, T., Graepel, T., Legg, S.: Symmetric decomposition of asymmetric games. Sci. Rep. 8(1), 1015 (2018)","journal-title":"Sci. Rep."},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Tuyls, K., Verbeeck, K., Lenaerts, T.: A selection-mutation model for q-learning in multi-agent systems. In: Proceedings of the Second International Joint Conference on Autonomous Agents & Multiagent Systems, AAMAS 2003, Melbourne, Victoria, Australia, 14\u201318 July, 2003, pp. 693\u2013700 (2003)","DOI":"10.1145\/860575.860687"},{"issue":"3","key":"1_CR44","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1609\/aimag.v33i3.2426","volume":"33","author":"K Tuyls","year":"2012","unstructured":"Tuyls, K., Weiss, G.: Multiagent learning: basics, challenges, and prospects. AI Mag. 33(3), 41\u201352 (2012)","journal-title":"AI Mag."},{"key":"1_CR45","unstructured":"Urzelai, J., Floreano, D.: Evolutionary robotics: coping with environment change. In: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2000), Las Vegas, Nevada, USA, 8\u201312 July, 2000, pp. 941\u2013948 (2000)"},{"key":"1_CR46","unstructured":"Weibull, J.W.: Evolutionary Game Theory. MIT Press, Cambridge (1997)"},{"key":"1_CR47","unstructured":"Wooldridge, M.J.: Introduction to Multiagent Systems. Wiley, Hoboken (2002)"},{"key":"1_CR48","unstructured":"Wunder, M., Littman, M.L., Babes, M.: Classes of multiagent q-learning dynamics with epsilon-greedy exploration. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), Haifa, Israel, 21\u201324 June, 2010, pp. 1167\u20131174 (2010)"}],"container-title":["Lecture Notes in Computer Science","Multi-Agent Systems and Agreement Technologies"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-01713-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T05:30:21Z","timestamp":1775280621000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-01713-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018]]},"ISBN":["9783030017125","9783030017132"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-01713-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018]]}}}