{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,11]],"date-time":"2025-07-11T10:44:58Z","timestamp":1752230698098,"version":"3.41.2"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[1998,11,1]],"date-time":"1998-11-01T00:00:00Z","timestamp":909878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[1998,11,1]],"date-time":"1998-11-01T00:00:00Z","timestamp":909878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Learning"],"published-print":{"date-parts":[[1998,11]]},"DOI":"10.1023\/a:1007570708568","type":"journal-article","created":{"date-parts":[[2002,12,22]],"date-time":"2002-12-22T05:04:10Z","timestamp":1040533450000},"page":"263-282","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":28,"title":["Learning Team Strategies: Soccer Case Studies"],"prefix":"10.1007","volume":"33","author":[{"given":"Rafa\u0142 P.","family":"Sa\u0142ustowicz","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marco A.","family":"Wiering","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00fcrgen","family":"Schmidhuber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"key":"186721_CR1","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1115\/1.3426922","volume":"97","author":"J.S. Albus","year":"1975","unstructured":"Albus, J.S. (1975). A new approach to manipulator control: The cerebellar model articulation controller (CMAC). Dynamic Systems, Measurement and Control, 97, 220\u2013227.","journal-title":"Dynamic Systems, Measurement and Control"},{"key":"186721_CR2","unstructured":"Asada, M., Uchibe, E., Noda, S., Tawaratsumida, S., & Hosoda, K. (1994). A vision-based reinforcement learning for coordination of soccer playing behaviors. Proceedings of AAAI-94 Workshop on AI and A-life and Entertainment (pp. 16\u201321)."},{"key":"186721_CR3","series-title":"Technical Report","volume-title":"Population-based incremental learning: A method for integrating genetic search based function optimization and competitive learning","author":"S. Baluja","year":"1994","unstructured":"Baluja, S. (1994). Population-based incremental learning: A method for integrating genetic search based function optimization and competitive learning (Technical Report CMU-CS-94-163), Carnegie Mellon University, Pittsburgh."},{"key":"186721_CR4","first-page":"38","volume-title":"Machine Learning: Proceedings of the Twelfth International Conference","author":"S. Baluja","year":"1995","unstructured":"Baluja, S., & Caruana, R. (1995). Removing the genetics from the standard genetic algorithm. In A. Prieditis, & S. Russell (Eds.), Machine Learning: Proceedings of the Twelfth International Conference (pp. 38\u201346). San Francisco, CA: Morgan Kaufmann Publishers."},{"key":"186721_CR5","volume-title":"Neuro-Dynamic Programming","author":"D.P. Bertsekas","year":"1996","unstructured":"Bertsekas, D.P., & Tsitsiklis, J.N. (1996). Neuro-Dynamic Programming. Belmont, MA: Athena Scientific."},{"key":"186721_CR6","first-page":"183","volume-title":"Proceedings of an International Conference on Genetic Algorithms and their Applications","author":"N.L. Cramer","year":"1985","unstructured":"Cramer, N.L. (1985). A representation for the adaptive generation of simple sequential programs. In J. Grefenstette (Ed.), Proceedings of an International Conference on Genetic Algorithms and their Applications (pp. 183\u2013187). Hillsdale, NJ: Lawrence Erlbaum Associates."},{"key":"186721_CR7","first-page":"1017","volume-title":"Advances in Neural Information Processing Systems","author":"R. Crites","year":"1996","unstructured":"Crites, R., & Barto, A. (1996). Improving elevator performance using reinforcement learning. In D. Touretzky, M. Mozer, & M. Hasselmo (Eds.), Advances in Neural Information Processing Systems (Vol. 8, pp. 1017\u20131023). Cambridge, MA: MIT Press."},{"key":"186721_CR8","unstructured":"Dickmanns, D., Schmidhuber, J., & Winklhofer, A. (1987). Der genetische Algorithmus: Eine Implementierung in Prolog. Fortgeschrittenenpraktikum, Institut f\u00fcr Informatik, Lehrstuhl Prof. Radig, Technische Universit\u00e4t M\u00fcnchen."},{"key":"186721_CR9","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4931.001.0001","volume-title":"Neural Network Learning and Expert Systems","author":"S.I. Gallant","year":"1993","unstructured":"Gallant, S.I. (1993). Neural Network Learning and Expert Systems. Cambridge, MA: MIT Press."},{"key":"186721_CR10","volume-title":"Genetic Programming\u2014On the Programming of Computers by Means of Natural Selection","author":"J.R. Koza","year":"1992","unstructured":"Koza, J.R. (1992). Genetic Programming\u2014On the Programming of Computers by Means of Natural Selection. Cambridge, MA: MIT Press."},{"issue":"3","key":"186721_CR11","first-page":"265","volume":"9","author":"L.A. Levin","year":"1973","unstructured":"Levin, L.A. (1973). Universal sequential search problems. Problems of Information Transmission, 9(3), 265\u2013266.","journal-title":"Problems of Information Transmission"},{"key":"186721_CR12","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/S0019-9958(84)80060-1","volume":"61","author":"L.A. Levin","year":"1984","unstructured":"Levin, L.A. (1984). Randomness conservation inequalities: Information and independence in mathematical theories. Information and Control, 61, 15\u201337.","journal-title":"Information and Control"},{"key":"186721_CR13","volume-title":"An Introduction to Kolmogorov Complexity and its Applications","author":"M. P. Li","year":"1993","unstructured":"Li, M., & Vit\u00e1nyi, P.M.B. (1993). An Introduction to Kolmogorov Complexity and its Applications. New York, NY: Springer-Verlag."},{"key":"186721_CR14","volume-title":"Reinforcement learning for robots using neural networks","author":"L.J. Lin","year":"1993","unstructured":"Lin, L.J. (1993). Reinforcement learning for robots using neural networks. Ph.D. thesis, Carnegie Mellon University, Pittsburgh, PA."},{"key":"186721_CR15","first-page":"157","volume-title":"Machine Learning: Proceedings of the Eleventh International Conference","author":"M.L. Littman","year":"1994","unstructured":"Littman, M.L. (1994). Markov games as a framework for multi-agent reinforcement learning. In A. Prieditis, & S. Russell (Eds.), Machine Learning: Proceedings of the Eleventh International Conference (pp. 157\u2013163). San Francisco, CA: Morgan Kaufmann Publishers."},{"key":"186721_CR16","doi-asserted-by":"crossref","unstructured":"Luke, S., Hohn, C., Farris, J., Jackson, G., & Hendler, J. (1997). Co-evolving soccer softbot team coordination with genetic programming. Proceedings of the First International Workshop on RoboCup, at the International Joint Conference on Artificial Intelligence (IJCAI-97).","DOI":"10.1007\/3-540-64473-3_76"},{"key":"186721_CR17","first-page":"63","volume-title":"Working Notes for the AAAI-96 Spring Symposium on Adaptation, Coevolution and Learning in Multi-agent Systems","author":"H. Matsubara","year":"1996","unstructured":"Matsubara, H., Noda, I., & Hiraki, K. (1996). Learning of cooperative actions in multi-agent systems: A case study of pass play in soccer. In S. Sen (Ed.), Working Notes for the AAAI-96 Spring Symposium on Adaptation, Coevolution and Learning in Multi-agent Systems (pp. 63\u201367). Menlo Park, CA: AAAI Press."},{"key":"186721_CR18","first-page":"137","volume-title":"Distributed Artificial Intelligence Meets Machine Learning. Learning in Multi-Agent Environments","author":"R. Nadella","year":"1996","unstructured":"Nadella, R., & Sen, S. (1996). Correlating internal parameters and external performance: Learning soccer agents. In G. Weiss (Ed.), Distributed Artificial Intelligence Meets Machine Learning. Learning in Multi-Agent Environments (pp. 137\u2013150). Berlin: Springer-Verlag."},{"key":"186721_CR19","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1162\/neco.1992.4.4.473","volume":"4","author":"S.J. Nowlan","year":"1992","unstructured":"Nowlan, S.J., & Hinton, G.E. (1992). Simplifying neural networks by soft weight sharing. Neural Computation, 4, 173\u2013193.","journal-title":"Neural Computation"},{"key":"186721_CR20","first-page":"283","volume":"22","author":"J. Peng","year":"1996","unstructured":"Peng, J., & Williams, R. (1996). Incremental multi-step Q-learning. Machine Learning, 22, 283\u2013290.","journal-title":"Machine Learning"},{"key":"186721_CR21","unstructured":"Sahota, M. (1993). Real-time intelligent behaviour in dynamic environments: Soccer-playing robots. Master's thesis, University of British Columbia."},{"issue":"2","key":"186721_CR22","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1162\/evco.1997.5.2.123","volume":"5","author":"R.P. Sa\u0142ustowicz","year":"1997","unstructured":"Sa\u0142ustowicz, R.P., & Schmidhuber, J. (1997). Probabilistic incremental program evolution. Evolutionary Compu-tation, 5(2), 123\u2013141.","journal-title":"Evolutionary Compu-tation"},{"key":"186721_CR23","first-page":"502","volume-title":"Proceedings of the Fourth International Conference on Neural Information Processing (ICONIP'97)","author":"R.P. Sa\u0142ustowicz","year":"1997","unstructured":"Sa\u0142ustowicz, R.P., Wiering, M.A., & Schmidhuber, J. (1997a). Evolving soccer strategies. Proceedings of the Fourth International Conference on Neural Information Processing (ICONIP'97) (pp. 502\u2013506). Singapore: Springer-Verlag."},{"key":"186721_CR24","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1007\/BFb0020247","volume-title":"Proceedings of the Seventh International Conference on Artificial Neural Networks (ICANN'97)","author":"R.P. Sa\u0142ustowicz","year":"1997","unstructured":"Sa\u0142ustowicz, R.P., Wiering, M.A., & Schmidhuber, J. (1997b). On learning soccer strategies. In W. Gerstner, A. Germond, M. Hasler, & J.-D. Nicoud (Eds.), Proceedings of the Seventh International Conference on Artificial Neural Networks (ICANN'97), volume 1327 of Lecture Notes in Computer Science (pp. 769\u2013774). Berlin Heidelberg: Springer-Verlag."},{"issue":"5","key":"186721_CR25","doi-asserted-by":"crossref","first-page":"857","DOI":"10.1016\/S0893-6080(96)00127-X","volume":"10","author":"J. Schmidhuber","year":"1997","unstructured":"Schmidhuber, J. (1997a). Discovering neural nets with low Kolmogorov complexity and high generalization capability. Neural Networks, 10(5), 857\u2013873.","journal-title":"Neural Networks"},{"key":"186721_CR26","unstructured":"Schmidhuber, J. (1997b). A general method for incremental self-improvement and multi-agent learning in unrestricted environments. In X. Yao (Ed.), Evolutionary Computation: Theory and Applications. Singapore: Scientific Publ. Co., in press."},{"key":"186721_CR27","first-page":"293","volume-title":"Learning to Learn","author":"J. Schmidhuber","year":"1997","unstructured":"Schmidhuber, J., Zhao, J., & Schraudolph, N. (1997a). Reinforcement learning with self-modifying policies. In S. Thrun & L. Pratt (Eds.), Learning to Learn (pp. 293\u2013309). Boston, MA: Kluwer."},{"key":"186721_CR28","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1023\/A:1007383707642","volume":"28","author":"J. Schmidhuber","year":"1997","unstructured":"Schmidhuber, J., Zhao, J., & Wiering, M. (1997b). Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning, 28, 105\u2013130.","journal-title":"Machine Learning"},{"key":"186721_CR29","doi-asserted-by":"crossref","unstructured":"Solomonoff, R. (1986). An application of algorithmic probability to problems in artificial intelligence. In L.N. Kanal & J.F. Lemmer (Eds.), Uncertainty in Artificial Intelligence (pp. 473\u2013491). Elsevier Science Publishers.","DOI":"10.1016\/B978-0-444-70058-2.50040-1"},{"key":"186721_CR30","first-page":"896","volume-title":"Advances in Neural Information Processing Systems","author":"P. Stone","year":"1996","unstructured":"Stone, P., & Veloso, M. (1996a). Beating a defender in robotic soccer: Memory-based learning of a continuous function. In G. Tesauro, D.S. Touretzky, & T.K. Leen (Eds.), Advances in Neural Information Processing Systems (Vol. 8, pp. 896\u2013902). Cambridge, MA: MIT Press."},{"key":"186721_CR31","doi-asserted-by":"crossref","unstructured":"Stone, P., & Veloso, M. (1996b). A layered approach to learning client behaviors in the robocup soccer server. Applied Artificial Intelligence (AAI), 1998, to appear.","DOI":"10.1080\/088395198117811"},{"key":"186721_CR32","first-page":"9","volume":"3","author":"R.S. Sutton","year":"1988","unstructured":"Sutton, R.S. (1988). Learning to predict by the methods of temporal differences. Machine Learning, 3, 9\u201344.","journal-title":"Machine Learning"},{"key":"186721_CR33","first-page":"1038","volume-title":"Advances in Neural Information Processing Systems","author":"R.S. Sutton","year":"1996","unstructured":"Sutton, R.S. (1996). Generalization in reinforcement learning: Successful examples using sparse coarse coding. In D.S. Touretzky, M.C. Mozer, & M.E. Hasselmo (Eds.), Advances in Neural Information Processing Systems (Vol. 8, pp. 1038\u20131045). Cambridge, MA: MIT Press."},{"key":"186721_CR34","unstructured":"Sutton, R.S. (1997). Personal communication at the Seventh International Conference on Artificial Neural Networks (ICANN'97)."},{"issue":"2","key":"186721_CR35","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1162\/neco.1994.6.2.215","volume":"6","author":"G. Tesauro","year":"1994","unstructured":"Tesauro, G. (1994). TD-gammon, a self-teaching backgammon program, achieves master-level play. Neural Computation, 6(2), 215\u2013219.","journal-title":"Neural Computation"},{"key":"186721_CR36","first-page":"40","volume-title":"DAI Meets Machine Learning","author":"C. Versino","year":"1997","unstructured":"Versino, C., & Gambardella, L.M. (1997). Learning real team solutions. In G. Weiss (Ed.), DAI Meets Machine Learning, volume 1221 of Lecture Notes in Artificial Intelligence (pp. 40\u201361). Berlin: Springer-Verlag."},{"key":"186721_CR37","volume-title":"Learning from Delayed Rewards","author":"C. Watkins","year":"1989","unstructured":"Watkins, C. (1989). Learning from Delayed Rewards. PhD thesis, King's College, Cambridge."},{"key":"186721_CR38","series-title":"Lecture Notes in Artificial Intelligence","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/3-540-60923-7","volume-title":"Adaptation and Learning in Multi-Agent Systems","author":"G. Weiss","year":"1996","unstructured":"Weiss, G. (1996). Adaptation and learning in multi-agent systems: Some remarks and a bibliography. In G.Weiss & S. Sen (Eds.), Adaptation and Learning in Multi-Agent Systems, volume 1042 of Lecture Notes in Artificial Intelligence (pp. 1\u201321). Berlin Heidelberg: Springer-Verlag."},{"key":"186721_CR39","first-page":"96","volume-title":"1960 IRE WESCON Convention Record","author":"B. Widrow","year":"1960","unstructured":"Widrow, B., & Hoff, M.E. (1960). Adaptive switching circuits. 1960 IRE WESCON Convention Record (Vol. 4, pp. 96\u2013104). New York: IRE. Reprinted in Anderson and Rosenfeld (1988)."},{"key":"186721_CR40","first-page":"534","volume-title":"Machine Learning: Proceedings of the Thirteenth International Conference","author":"M.A. Wiering","year":"1996","unstructured":"Wiering, M.A., & Schmidhuber, J. (1996). Solving POMDPs with Levin search and EIRA. In L. Saitta (Ed.), Machine Learning: Proceedings of the Thirteenth International Conference (pp. 534\u2013542). San Francisco, CA: Morgan Kaufmann Publishers."},{"key":"186721_CR41","series-title":"Technical Report","volume-title":"Fast online Q(\u03bb)","author":"M.A. Wiering","year":"1997","unstructured":"Wiering, M.A., & Schmidhuber, J. (1997). Fast online Q(\u03bb) (Technical Report IDSIA-21-97), IDSIA,Lugano, Switzerland."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007570708568.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1023\/A:1007570708568\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1023\/A:1007570708568.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T11:31:28Z","timestamp":1752147088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1023\/A:1007570708568"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1998,11]]},"references-count":41,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[1998,11]]}},"alternative-id":["186721"],"URL":"https:\/\/doi.org\/10.1023\/a:1007570708568","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[1998,11]]},"assertion":[{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}