{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,22]],"date-time":"2026-02-22T10:52:57Z","timestamp":1771757577968,"version":"3.50.1"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2016,11,26]],"date-time":"2016-11-26T00:00:00Z","timestamp":1480118400000},"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":["Auton Agent Multi-Agent Syst"],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1007\/s10458-016-9352-6","type":"journal-article","created":{"date-parts":[[2016,11,26]],"date-time":"2016-11-26T14:49:16Z","timestamp":1480171756000},"page":"767-789","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Efficiently detecting switches against non-stationary opponents"],"prefix":"10.1007","volume":"31","author":[{"given":"Pablo","family":"Hernandez-Leal","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yusen","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matthew E.","family":"Taylor","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L. Enrique","family":"Sucar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Enrique","family":"Munoz de Cote","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,11,26]]},"reference":[{"issue":"1","key":"9352_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. (2008). A multiagent reinforcement learning algorithm with non-linear dynamics. Journal of Artificial Intelligence Research, 33(1), 521\u2013549.","journal-title":"Journal of Artificial Intelligence Research"},{"key":"9352_CR2","unstructured":"Adams, R. P., & MacKay, D. (2007). Bayesian online changepoint detection. arXiv:0710.3742v1 [stat.ML]"},{"key":"9352_CR3","unstructured":"Albrecht, S. V., & Ramamoorthy, S. (2013). A game-theoretic model and best-response learning method for ad hoc coordination in multiagent systems. In Proceedings of 15th international conference on autonomous agents and multiagent systems (pp. 1155\u20131156)."},{"key":"9352_CR4","doi-asserted-by":"crossref","unstructured":"Almeida, A., Ramalho, G., Santana, H., Tedesco, P., Menezes, T., Corruble, V., Chevaleyre, Y. (2004). Recent advances on multi-agent patrolling. In Advances in artificial intelligence\u2014SBIA 2004 (pp. 474\u2013483). IEEE.","DOI":"10.1007\/978-3-540-28645-5_48"},{"issue":"27","key":"9352_CR5","doi-asserted-by":"crossref","first-page":"1390","DOI":"10.1126\/science.7466396","volume":"211","author":"R Axelrod","year":"1981","unstructured":"Axelrod, R., & Hamilton, W. D. (1981). The evolution of cooperation. Science, 211(27), 1390\u20131396.","journal-title":"Science"},{"key":"9352_CR6","doi-asserted-by":"crossref","unstructured":"Banerjee, B., & Peng, J. (2005). Efficient learning of multi-step best response. In Proceedings of the 4th international conference on autonomous agents and multiagent systems (pp. 60\u201366). Utretch: ACM.","DOI":"10.1145\/1082473.1082483"},{"key":"9352_CR7","unstructured":"Barrett, S., & Stone, P. (2014). Cooperating with unknown teammates in complex domains: A robot soccer case study of Ad Hoc teamwork. In Twenty-ninth AAAI conference on artificial intelligence (pp. 2010\u20132016). Austin, Texas."},{"issue":"5","key":"9352_CR8","first-page":"679","volume":"6","author":"R Bellman","year":"1957","unstructured":"Bellman, R. (1957). A Markovian decision process. Journal of Mathematics and Mechanics, 6(5), 679\u2013684.","journal-title":"Journal of Mathematics and Mechanics"},{"key":"9352_CR9","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1126\/science.1259433","volume":"347","author":"M Bowling","year":"2015","unstructured":"Bowling, M., Burch, N., Johanson, M., & Tammelin, O. (2015). Heads-up limit hold\u2019em poker is solved. Science, 347, 145\u2013149.","journal-title":"Science"},{"issue":"2","key":"9352_CR10","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1016\/S0004-3702(02)00121-2","volume":"136","author":"M Bowling","year":"2002","unstructured":"Bowling, M., & Veloso, M. (2002). Multiagent learning using a variable learning rate. Artificial Intelligence, 136(2), 215\u2013250.","journal-title":"Artificial Intelligence"},{"key":"9352_CR11","first-page":"213","volume":"3","author":"RI Brafman","year":"2003","unstructured":"Brafman, R. I., & Tennenholtz, M. (2003). R-MAX a general polynomial time algorithm for near-optimal reinforcement learning. The Journal of Machine Learning Research, 3, 213\u2013231.","journal-title":"The Journal of Machine Learning Research"},{"issue":"1","key":"9352_CR12","first-page":"374","volume":"13","author":"GW Brown","year":"1951","unstructured":"Brown, G. W. (1951). Iterative solution of games by fictitious play. Activity Analysis of Production and Allocation, 13(1), 374\u2013376.","journal-title":"Activity Analysis of Production and Allocation"},{"issue":"2","key":"9352_CR13","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1109\/TSMCC.2007.913919","volume":"38","author":"L Busoniu","year":"2008","unstructured":"Busoniu, L., Babuska, R., & De\u00a0Schutter, B. (2008). A comprehensive survey of multiagent reinforcement learning. IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 38(2), 156\u2013172.","journal-title":"IEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews)"},{"issue":"2","key":"9352_CR14","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1007\/s10458-013-9222-4","volume":"28","author":"D Chakraborty","year":"2013","unstructured":"Chakraborty, D., & Stone, P. (2013). Multiagent learning in the presence of memory-bounded agents. Autonomous Agents and Multi-agent Systems, 28(2), 182\u2013213.","journal-title":"Autonomous Agents and Multi-agent Systems"},{"key":"9352_CR15","unstructured":"Choi, S. P. M., Yeung, D. Y., Zhang, N. L. (1999). An environment model for nonstationary reinforcement learning. In Advances in neural information processing systems (pp. 987\u2013993). Denver, Colorado."},{"issue":"1\u20132","key":"9352_CR16","first-page":"23","volume":"67","author":"V Conitzer","year":"2006","unstructured":"Conitzer, V., & Sandholm, T. (2006). AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents. Machine Learning, 67(1\u20132), 23\u201343.","journal-title":"Machine Learning"},{"issue":"3","key":"9352_CR17","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1007\/s10994-010-5192-9","volume":"82","author":"JW Crandall","year":"2011","unstructured":"Crandall, J. W., & Goodrich, M. A. (2011). Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning. Machine Learning, 82(3), 281\u2013314.","journal-title":"Machine Learning"},{"key":"9352_CR18","doi-asserted-by":"crossref","unstructured":"Da\u00a0Silva, B. C., Basso, E. W., Bazzan, A. L., Engel, P. M. (2006). Dealing with non-stationary environments using context detection. In Proceedings of the 23rd international conference on machine learnig (pp. 217\u2013224). Pittsburgh, Pennsylvania.","DOI":"10.1145\/1143844.1143872"},{"key":"9352_CR19","unstructured":"de Cote, E. M., Chapman, A. C., Sykulski, A. M., Jennings, N. R. (2010). Automated planning in repeated adversarial games. In Uncertainty in artificial intelligence (pp. 376\u2013383). Catalina Island, California."},{"key":"9352_CR20","unstructured":"Doshi, P., & Gmytrasiewicz, P. J. (2006). On the difficulty of achieving equilibrium in interactive POMDPs. In Twenty-first national conference on artificial intelligence (pp. 1131\u20131136). Boston, MA."},{"key":"9352_CR21","unstructured":"Elidrisi, M., Johnson, N., Gini, M., Crandall, J. W. (2014). Fast adaptive learning in repeated stochastic games by game abstraction. In Proceedings of the 13th international conference on autonomous agents and multiagent systems (pp. 1141\u20131148). Paris."},{"key":"9352_CR22","unstructured":"Fulda, N., & Ventura, D. (2007). Predicting and preventing coordination problems in cooperative Q-learning systems. In Proceedings of the twentieth international joint conference on artificial intelligence (pp. 780\u2013785). Hyderabad."},{"key":"9352_CR23","doi-asserted-by":"crossref","unstructured":"Gama, J., Medas, P., Castillo, G., Rodrigues, P. (2004). Learning with drift detection. In Advances in artificial intelligence\u2014SBIA (pp. 286\u2013295).","DOI":"10.1007\/978-3-540-28645-5_29"},{"issue":"4","key":"9352_CR24","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1145\/2523813","volume":"46","author":"J Gama","year":"2014","unstructured":"Gama, J., Zliobaite, I., Bifet, A., Pechenizkiy, M., & Bouchachia, A. (2014). A survey on concept drift adaptation. ACM Computing Surveys (CSUR), 46(4), 44.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"9352_CR25","unstructured":"Hernandez-Leal, P., Munoz\u00a0de Cote, E., Sucar, L. E. (2014). Exploration strategies to detect strategy switches. In Proceedings of the adaptive learning agents workshop (ALA). Paris"},{"key":"9352_CR26","unstructured":"Hernandez-Leal, P., Rosman, B., Taylor, M. E., Sucar, L. E., Munoz\u00a0de Cote, E.(2016). A Bayesian approach for learning and tracking switching, non-stationary opponents (extended abstract). In Proceedings of 15th international conference on autonomous agents and multiagent systems (pp. 1315\u20131316). Singapore."},{"key":"9352_CR27","unstructured":"Hernandez-Leal, P., Taylor, M. E., Rosman, B., Sucar, L. E., Munoz\u00a0de Cote, E. (2016). Identifying and tracking switching, non-stationary opponents: A Bayesian approach. In Multiagent interaction without prior coordination workshop at AAAI. Phoenix, AZ"},{"issue":"2","key":"9352_CR28","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1080\/09540091.2014.885294","volume":"26","author":"P Hernandez-Leal","year":"2014","unstructured":"Hernandez-Leal, P., Munoz de Cote, E., & Sucar, L. E. (2014). A framework for learning and planning against switching strategies in repeated games. Connection Science, 26(2), 103\u2013122.","journal-title":"Connection Science"},{"key":"9352_CR29","doi-asserted-by":"crossref","unstructured":"Hido, S., Id\u00e9, T., Kashima, H., Kubo, H., Matsuzawa, H. (2008). Unsupervised change analysis using supervised learning. In Advances in knowledge discovery and data mining (pp. 148\u2013159). Berlin: Springer.","DOI":"10.1007\/978-3-540-68125-0_15"},{"key":"9352_CR30","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1016\/j.eneco.2013.04.015","volume":"39","author":"W Ketter","year":"2013","unstructured":"Ketter, W., Collins, J., & Reddy, P. P. (2013). Power TAC: A competitive economic simulation of the smart grid. Energy Economics, 39, 262\u2013270.","journal-title":"Energy Economics"},{"key":"9352_CR31","volume-title":"The 2014 power trading agent competition","author":"W Ketter","year":"2014","unstructured":"Ketter, W., Collins, J., Reddy, P. P., & Weerdt, M. D. (2014). The 2014 power trading agent competition. Rotterdam: Department of Decision and Information Sciencies, Erasmus University."},{"key":"9352_CR32","doi-asserted-by":"crossref","unstructured":"Littman, M. L. (1994). Markov games as a framework for multi-agent reinforcement learning. In Proceedings of the 11th international conference on machine learning (pp. 157\u2013163). New Brunswick, NJ.","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"9352_CR33","unstructured":"Littman, M. L., & Stone, P.(2001). Implicit negotiation in repeated games. In ATAL \u201901: Revised papers from the 8th international workshop on intelligent agents VIII."},{"issue":"1","key":"9352_CR34","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1073\/pnas.36.1.48","volume":"36","author":"JF Nash","year":"1950","unstructured":"Nash, J. F. (1950). Equilibrium points in n-person games. Proceedings of the National Academy of Sciences, 36(1), 48\u201349.","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"9352_CR35","unstructured":"Nudelman, E., Wortman, J., Shoham, Y., Leyton-Brown, K. (2004). Run the GAMUT: A comprehensive approach to evaluating game-theoretic algorithms. In Proceedings of the 3rd international conference on autonomous agents and multiagent systems (pp. 880\u2013887). New York, NY."},{"issue":"3","key":"9352_CR36","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1287\/moor.12.3.441","volume":"12","author":"CH Papadimitriou","year":"1987","unstructured":"Papadimitriou, C. H., & Tsitsiklis, J. N. (1987). The complexity of Markov decision processes. Mathematics of Operations Research, 12(3), 441\u2013450.","journal-title":"Mathematics of Operations Research"},{"key":"9352_CR37","unstructured":"Powers, R., & Shoham, Y. (2005). Learning against opponents with bounded memory. In Proceedings of the 19th international joint conference on artificial intelligence (pp. 817\u2013822). Edinburg: Morgan Kaufmann Publishers Inc."},{"key":"9352_CR38","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316887","volume-title":"Markov decision processes: Discrete stochastic dynamic programming","author":"M Puterman","year":"1994","unstructured":"Puterman, M. (1994). Markov decision processes: Discrete stochastic dynamic programming. New York: Wiley."},{"key":"9352_CR39","doi-asserted-by":"crossref","unstructured":"Rosman, B., Hawasly, M., Ramamoorthy, S. (2016). Bayesian policy reuse. Machine Learning, 104(1), 99\u2013127.","DOI":"10.1007\/s10994-016-5547-y"},{"key":"9352_CR40","first-page":"1633","volume":"10","author":"ME Taylor","year":"2009","unstructured":"Taylor, M. E., & Stone, P. (2009). Transfer learning for reinforcement learning domains: A survey. The Journal of Machine Learning Research, 10, 1633\u20131685.","journal-title":"The Journal of Machine Learning Research"},{"key":"9352_CR41","doi-asserted-by":"crossref","unstructured":"Tesauro, G., & Bredin, J. L. (2002). Strategic sequential bidding in auctions using dynamic programming. In Proceedings of the 1st international conference on autonomous agents and multiagent systems (p. 591). Bologna: ACM Request Permissions.","DOI":"10.1145\/544862.544885"},{"key":"9352_CR42","doi-asserted-by":"crossref","unstructured":"Urieli, D., & Stone, P. (2014). TacTex 13: A champion adaptive power trading agent. In Proceedings of the twenty-eighth conference on artificial intelligence (pp. 465\u2013471). Quebec.","DOI":"10.1609\/aaai.v28i1.8767"},{"key":"9352_CR43","first-page":"279","volume":"8","author":"C Watkins","year":"1992","unstructured":"Watkins, C., & Dayan, P. (1992). Q-learning. Machine Learning, 8, 279\u2013292.","journal-title":"Machine Learning"},{"issue":"1","key":"9352_CR44","first-page":"69","volume":"23","author":"G Widmer","year":"1996","unstructured":"Widmer, G., & Kubat, M. (1996). Learning in the presence of concept drift and hidden contexts. Machine Learning, 23(1), 69\u2013101.","journal-title":"Machine Learning"},{"issue":"158","key":"9352_CR45","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1080\/01621459.1927.10502953","volume":"22","author":"EB Wilson","year":"1927","unstructured":"Wilson, E. B. (1927). Probable inference, the law of succesion, and statistical inference. Journal of the American Statistical Association, 22(158), 209\u2013212.","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"9352_CR46","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/S0167-9236(98)00060-8","volume":"24","author":"PR Wurman","year":"1998","unstructured":"Wurman, P. R., Walsh, W. E., & Wellman, M. (1998). Flexible double auctions for electronic commerce: Theory and implementation. Decision Support Systems, 24(1), 17\u201327.","journal-title":"Decision Support Systems"},{"key":"9352_CR47","unstructured":"Yamada, M., Kimura, A., Naya, F., Sawada, H. (2013). Change-point detection with feature selection in high-dimensional time-series data. In Proceedings of the 23rd international joint conference on artificial intelligence (pp. 1827\u20131833). Bellevue, Washington."}],"container-title":["Autonomous Agents and Multi-Agent Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10458-016-9352-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-016-9352-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10458-016-9352-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T00:32:47Z","timestamp":1657845167000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10458-016-9352-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,11,26]]},"references-count":47,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2017,7]]}},"alternative-id":["9352"],"URL":"https:\/\/doi.org\/10.1007\/s10458-016-9352-6","relation":{},"ISSN":["1387-2532","1573-7454"],"issn-type":[{"value":"1387-2532","type":"print"},{"value":"1573-7454","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,11,26]]}}}