Abstract
We use reinforcement learning (RL) to compute strategies for multiagent soccer teams. RL may profit significantly from world models (WMs) estimating state transition probabilities and rewards. In high-dimensional, continuous input spaces, however, learning accurate WMs is intractable. Here we show that incomplete WMs can help to quickly find good action selection policies. Our approach is based on a novel combination of CMACs and prioritized sweeping-like algorithms. Variants thereof outperform both Q(λ)-learning with CMACs and the evolutionary method Probabilistic Incremental Program Evolution (PIPE) which performed best in previous comparisons.
Similar content being viewed by others
References
Albus, J.S. 1975. A new approach to manipulator control: The cerebellar model articulation controller (CMAC). Dynamic Systems, Measurement and Control, pp. 220-227.
Baluja, S. and Caruana, R. 1995. Removing the genetics from the standard genetic algorithm. In Machine Learning: Proceedings of the Twelfth International Conference, A. Prieditis and S. Russell (Eds.), Morgan Kaufmann Publishers: San Francisco, CA, pp. 38-46.
Barto, A.G., Sutton, R.S., and Anderson, C.W. 1983. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics, SMC-13:834-846.
Bellman, R. 1961. Adaptive Control Processes, Princeton University Press.
Bertsekas, D.P. and Tsitsiklis, J.N. 1996. Neuro-Dynamic Programming, Athena Scientific: Belmont, MA.
Chapman, D. and Kaelbling, L.P. 1991. Input generalization in delayed reinforcement learning. In Proceedings of the 13th International Joint Conference on Artificial Intelligence (IJCAI), Morgan Kaufman, Vol. 2, pp. 726-731.
Cramer, N.L. 1985. A representation for the adaptive generation of simple sequential programs. In Proceedings of an International Conference on Genetic Algorithms and Their Applications, J.J. Grefenstette (Ed.), Lawrence Erlbaum Associates: Hillsdale, NJ, pp. 183-187.
Dickmanns, D., Schmidhuber, J., and Winklhofer, A. 1986. Der genetische Algorithmus: Eine Implementierung in Prolog. Fortgeschrittenenpraktikum, Institut für Informatik, Lehrstuhl Prof. Radig, Technische Universität München.
Holland, J.H. 1975. Adaptation in Natural and Artificial Systems, University of Michigan Press: Ann Arbor.
Kaelbling, L. 1993. Learning in Embedded Systems, MIT Press.
Kearns, M. and Singh, S. 1999. Finite-sample convergence rates for Q-learning and indirect algorithms. In Advances in Neural Information Processing Systems 12, M. Kearns, S.A. Solla, and D. Cohn (Eds.), MIT Press: Cambridge, MA.
Koza, J.R. 1992. Genetic evolution and co-evolution of computer programs. In Artificial Life II, C.G. Langton, C. Taylor, J.D. Farmer, and S. Rasmussen (Eds.), Addison Wesley Publishing Company, pp. 313-324.
Lin, L.-J. 1993. Reinforcement Learning for Robots Using Neural Networks. Ph.D. Thesis, Carnegie Mellon University, Pittsburgh.
Moore, A. and Atkeson, C.G. 1993. Prioritized sweeping: Reinforcement learning with less data and less time. Machine Learning, 13:103-130.
Nowlan, S.J. and Hinton, G.E. 1992. Simplifying neural networks by soft weight sharing. Neural Computation, 4:173-193.
Peng, J. and Williams, R. 1996. Incremental multi-step Q-learning. Machine Learning, 22:283-290.
Rechenberg, I. 1971. Evolutions strategie—Optimierung technischer Systeme nach Prinzipien der biologischen Evolution, Dissertation, Published in 1973 by Fromman-Holzboog.
Rummery, G.A. and Niranjan, M. 1994. On-line Q-learning using connectionist sytems. Technical Report CUED/F-INFENG-TR 166, Cambridge University, UK.
Sałustowicz, R.P. and Schmidhuber, J. 1997. Probabilistic incremental program evolution. Evolutionary Computation, 5(2):123-141.
Sałustowicz, R.P., Wiering, M.A., and Schmidhuber, J. 1997a. Evolving soccer strategies. In Proceedings of the Fourth International Conference on Neural Information Processing (ICONIP'97), Springer-Verlag: Singapore, pp. 502-506.
Sałustowicz, R.P., Wiering, M.A., and Schmidhuber, J. 1997b. On learning soccer strategies. In Proceedings of the Seventh International Conference on Artificial Neural Networks (ICANN'97), volume 1327 of Lecture Notes in Computer Science, W. Gerstner, A. Germond, M. Hasler, and J.-D. Nicoud (Eds.), Springer-Verlag: Berlin, Heidelberg, pp. 769-774.
Sałustowicz, R.P., Wiering, M.A., and Schmidhuber, J. 1998. Learning team strategies: Soccer case studies. Machine Learning, 33(2/3):263-282.
Samuel, A.L. 1959. Some studies in machine learning using the game of checkers. IBM Journal on Research and Development, 3:210-229.
Santamaria, J.C., Sutton, R.S., and Ram, A. 1996. Experiments with reinforcement learning in problems with continuous state and action spaces. Technical Report CIONS 96-088, Georgia Institute of Technology, Atlanta.
Schmidhuber, J. 1995. On learning how to learn learning strategies. Technical Report FKI-198-94, Fakultät für Informatik, Technische Universität München, Revised January 1995.
Schmidhuber, J., Zhao, J., and Schraudolph, N. 1997a. Reinforcement learning with self-modifying policies. In Learning to Learn, S. Thrun and L. Pratt (Eds.), Kluwer, pp. 293-309.
Schmidhuber, J., Zhao, J., and Wiering, M. 1997b. Shifting inductive bias with success-story algorithm, adaptive Levin search, and incremental self-improvement. Machine Learning, 28:105-130.
Singh, S.P. and Sutton, R.S. 1996. Reinforcement learning with replacing eligibility traces. Machine Learning, 22:123-158.
Sutton, R.S. 1988. Learning to predict by the methods of temporal differences. Machine Learning, 3:9-44.
Sutton, R.S. 1996. Generalization in reinforcement learning: Successful examples using sparse coarse coding. In Advances in Neural Information Processing Systems 8, D.S. Touretzky, M.C. Mozer, and M.E. Hasselmo (Eds.), MIT Press: Cambridge, MA, pp. 1038-1045.
Sutton, R.S. and Barto, A.G. 1988. Reinforcement Learning: An Introduction, MIT Press/Bradford Books.
Thrun, S., Fox, D., and Burgard, W. 1998. A probabilistic approach to concurrent mapping and localization for mobile robots. Machine Learning, (31):29-53. Also appeared in Autonomous Robots, 5:253–271, 1998 as joint issue.
Watkins, C.J.C.H. 1989. Learning from Delayed Rewards. Ph.D. Thesis, King's College, Cambridge, England.
Watkins, C.J.C.H. and Dayan, P. 1992. Q-learning. Machine Learning, 8:279-292.
Wiering, M.A. 1999. Explorations in Efficient Reinforcement Learning. Ph.D. Thesis, University of Amsterdam/IDSIA.
Wiering, M.A. and Schmidhuber, J. 1998a. Efficient model-based exploration. In Proceedings of the Sixth International Conference on Simulation of Adaptive Behavior: From Animals to Animats 6, J.A. Meyer and S.W. Wilson (Eds.), MIT Press/Bradford Books, pp. 223-228.
Wiering, M.A. and Schmidhuber, J. 1998b. Fast online Q(λ). Machine Learning, 33(1):105-116.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Wiering, M., Sałustowicz, R. & Schmidhuber, J. Reinforcement Learning Soccer Teams with Incomplete World Models. Autonomous Robots 7, 77–88 (1999). https://doi.org/10.1023/A:1008921914343
Issue Date:
DOI: https://doi.org/10.1023/A:1008921914343