Evolution, neural networks, games, and intelligence

Mathematical games provide a framework for studying intelligent behavior in models of real-world settings or restricted domains. The obstacle comes in choosing the appropriate representation and learning algorithm. Neural networks and evolutionary algorithms provide useful means for addressing these issues. This paper describes efforts to hybridize neural and evolutionary computation to learn appropriate strategies in zero- and nonzero-sum games, including the iterated prisoner's dilemma, tic-tac-toe, and checkers. With respect to checkers, the evolutionary algorithm was able to discover a neural network that can be used to play at a near-expert level without injecting expert knowledge about how to play the game. The implications of evolutionary learning with respect to machine intelligence are also discussed. It is argued that evolution provides the framework for explaining naturally occurring intelligent entities and can be used to design machines that are also capable of intelligent behavior.

[1]  E. Thorndike.  On the Organization of Intellect. , 1921 .

[2]  J. Neumann,et al.  Theory of Games and Economic Behavior. , 1945 .

[3]  George H. Mealy,et al.  A method for synthesizing sequential circuits , 1955 .

[4]  J. Sayer Minas,et al.  Some descriptive aspects of two-person non-zero-sum games , 1959 .

[5]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[6]  Nils Aall Barricelli,et al.  Numerical testing of evolution theories , 1963 .

[7]  L ORNSTEIN,et al.  COMPUTER LEARNING AND THE SCIENTIFIC METHOD: A PROPOSED SOLUTION TO THE INFORMATION THEORETICAL PROBLEM OF MEANING. , 1965, Journal of the Mount Sinai Hospital, New York.

[8]  Edward Bryan Carne.  Artificial intelligence techniques , 1965 .

[9]  Lawrence J. Fogel,et al.  Artificial Intelligence through Simulated Evolution , 1966 .

[10]  A. Rapoport.  Optimal policies for the Prisoner's Dilemma. , 1967, Psychological review.

[11]  J. Reed,et al.  Simulation of biological evolution and machine learning. I. Selection of self-reproducing numeric patterns by data processing machines, effects of hereditary control, mutation type and crossing. , 1967, Journal of theoretical biology.

[12]  George H. Burgin,et al.  COMPETITIVE GOAL-SEEKING THROUGH EVOLUTIONARY?PROGRAMMING. , 1969 .

[13]  M. Conrad,et al.  Evolution experiments with an artificial ecosystem. , 1970, Journal of theoretical biology.

[14]  J M Smith,et al.  Evolution and the theory of games , 1976 .

[15]  J. W. Atmar,et al.  Speculation on the evolution of intelligence and its possible realization in machine form. , 1976 .

[16]  R. Axelrod.  More Effective Choice in the Prisoner's Dilemma , 1980 .

[17]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[18]  W. Hamilton,et al.  The evolution of cooperation. , 1984, Science.

[19]  David M. Kreps,et al.  Rational cooperation in the finitely repeated prisoners' dilemma , 1982 .

[20]  D. Hofstadter.  Metamagical Themas: Questing for the Essence of Mind and Pattern , 1985 .

[21]  Brian D. O. Anderson,et al.  Stability of adaptive systems: passivity and averaging analysis , 1986 .

[22]  Michael R. Genesereth,et al.  Logical foundations of artificial intelligence , 1987 .

[23]  Lennart Ljung,et al.  System Identification: Theory for the User , 1987 .

[24]  R. Boyd,et al.  No pure strategy is evolutionarily stable in the repeated Prisoner's Dilemma game , 1987, Nature.

[25]  T. To.  More Realism in the Prisoner's Dilemma , 1988 .

[26]  Robert E. Marks,et al.  Breeding hybrid strategies: optimal behaviour for oligopolists , 1989, ICGA.

[27]  H. Kaindl,et al.  Tree Searching Algorithms , 1990 .

[28]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[29]  D. Fogel.  System Identification Through Simulated Evolution: A Machine Learning Approach to Modeling , 1991 .

[30]  G. Reeke.  The society of mind , 1991 .

[31]  Jonathan Schaeffer,et al.  A World Championship Caliber Checkers Program , 1992, Artif. Intell..

[32]  David B. Fogel,et al.  Evolving Behaviors in the Iterated Prisoner's Dilemma , 1993, Evolutionary Computation.

[33]  J. Sutherland.  The Quark and the Jaguar , 1994 .

[34]  P. Angeline.  An Alternate Interpretation of the Iterated Prisoner ' s Dilemma and the Evolution of Non-Mutual Cooperation Peter , 1994 .

[35]  David B. Fogel,et al.  Evolutionary Computation: Towards a New Philosophy of Machine Intelligence , 1995 .

[36]  David B. Fogel,et al.  On the Relationship between the Duration of an Encounter and the Evolution of Cooperation in the Iterated Prisoner's Dilemma , 1995, Evolutionary Computation.

[37]  Mark D. Smucker,et al.  Iterated Prisoner's Dilemma with Choice and Refusal of Partners: Evolutionary Results , 1995, ECAL.

[38]  Jonathan Schaeffer,et al.  CHINOOK: The World Man-Machine Checkers Champion , 1996, AI Mag..

[39]  Charles Cole,et al.  Fluid concepts and creative analogies: Computer models of the fundamental mechanisms of thought , 1996 .

[40]  D. Fogel,et al.  Evolving continuous behaviors in the Iterated Prisoner's Dilemma. , 1996, Bio Systems.

[41]  Jonathan Schaeffer,et al.  One jump ahead - challenging human supremacy in checkers , 1997, J. Int. Comput. Games Assoc..

[42]  Thomas Bäck,et al.  Evolutionary computation: Toward a new philosophy of machine intelligence , 1997, Complex..

[43]  David B. Fogel,et al.  Evolutionary Computation: The Fossil Record , 1998 .

[44]  Peter J. Angeline,et al.  Evolving predictors for chaotic time series , 1998, Defense, Security, and Sensing.

[45]  David B. Fogel,et al.  Evolving neural networks to play checkers without relying on expert knowledge , 1999, IEEE Trans. Neural Networks.

[46]  Lawrence J. Fogel,et al.  Intelligence Through Simulated Evolution: Forty Years of Evolutionary Programming , 1999 .

[47]  Robert Axelrod,et al.  The Evolution of Strategies in the Iterated Prisoner's Dilemma , 2001 .