Abstract
A coupled dynamical recognizer is proposed as a model for simulating intelligent game players, who can imitate the other player’s behavior. A kind of recurrent neural network called a dynamical recognizer is used as an internal model of the other player to imitate the behavior. The Rashevskyan game is examined, where each player moves along a separate spatial axis to take an advantageous position over the other player. Though the players are egocentric in principle, it is shown that some altruistic behavior will be performed as a dynamical attractor phase. The altruistic behavior is no longer attainable by continually modeling the opponent player merely as a Tit for Tat player. Rather, players have to dynamically change their model of imitation to achieve mutual co-operation, otherwise they go to a static non-cooperative Nash solution. Enhancement of a minute difference in players’ action patterns, called the pragmatic paradox, is the key issue throughout this paper.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Akiyama, E., Ph.D thesis Dynamical Systems Game and Dynamics of games (The graduate School of Arts and Sciences, University of Tokyo, 1998).
Anderelini, L., Some Notes on Church’s Thesis and the Theory of the Games. Theory and Decision 29 (1990) pp.19–52.
Axelrod, R., The Evolution of Cooperation, (Basic Books, New York) 1984.
Bacharach, M., The Epistemic Structure of a Theory of a Game. in Epistemic Logic and the Theory of Games and Decisions (eds. M.O.L. Bacharach et al., Kluwer Acad. publ. 1997) pp. 303–344.
Bateson, G., Steps to an Ecology of Mind (Ballentine, New York 1972).
Binmore, K., Modeling Rational Players I. Economics and Philosophy 3 (1987) pp.179–214.
Dubey, P., Inefficiency of Nash Equilibria. Math. Oper. Res. 11 (1986) pp. 1–8.
Elman, J., Language as a Dynamical System in Mind as Motion (eds. R.E. Port and T. van Gelder, MIT press 1995) pp.195–226.
Ikegami, T., Taiji, M. Structures of Possible Worlds in a Game of Players with Internal Models. Acta Poly. Scan. Ma. 91. 283–292. 1998.
Pollack, J. B., The induction of dynamical recognizers. Machine Learning, 7:227–252, 1991.
Rashevsky, N., A problem in mathematical biophysics of interactions of two or more players which may be of interest in mathematical sociology. Bull. Math. Biophys. 9 (1947) pp. 9–15.
Rapoport, A., Mathematical theory of motivation interaction of two individuals. Bull. Math. Biophy. 9 (1947) pp.17–27.
Rössler, O.E., Fraiberg-Lenneberg Speech, Chaos, Soliton and Fractals 4 (1994) pp.125–131.
Rubinstein, A., Finite Automata play the repeated prisoner’s dilemma, J. Econ. Theory 36 (1986) pp.83–96.
Taiji, M. and Ikegami, T., Dynamics of Internal Models in Game Players. (Physica D in press).
Tani, J. and Fukumura, N., Self-organizing Internal Representation in Learning of Navigation: A Physical Experiment by the Mobile Robot YAMABICO, Neural Networks, Vol. 10, No. 1, pp. 153–159. 1997.
Tani, J., An Interpretation of the’ Self from the Dynamical Systems Perspective: A Constructivist Approach. Journal of Consciousness Studies, Vol.5 No.5–6, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ikegami, T., Taiji, M. (1999). Imitation and Cooperation in Coupled Dynamical Recognizers. In: Floreano, D., Nicoud, JD., Mondada, F. (eds) Advances in Artificial Life. ECAL 1999. Lecture Notes in Computer Science(), vol 1674. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-48304-7_73
Download citation
DOI: https://doi.org/10.1007/3-540-48304-7_73
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66452-9
Online ISBN: 978-3-540-48304-5
eBook Packages: Springer Book Archive