An Approach to Bounded Rationality

A central question in game theory and artificial intelligence is how a rational agent should behave in a complex environment, given that it cannot perform unbounded computations. We study strategic aspects of this question by formulating a simple model of a game with additional costs (computational or otherwise) for each strategy. First we connect this to zero-sum games, proving a counter-intuitive generalization of the classic min-max theorem to zero-sum games with the addition of strategy costs. We then show that potential games with strategy costs remain potential games. Both zero-sum and potential games with strategy costs maintain a very appealing property: simple learning dynamics converge to equilibrium.

[1]  E. Kalai.  Bounded Rationality and Strategic Complexity in Repeated Games , 1987 .

[2]  Paul W. Goldberg,et al.  The complexity of computing a Nash equilibrium , 2006, STOC '06.

[3]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[4]  Xi Chen,et al.  Computing Nash Equilibria: Approximation and Smoothed Complexity , 2006, 2006 47th Annual IEEE Symposium on Foundations of Computer Science (FOCS'06).

[5]  S. Hart,et al.  A General Class of Adaptive Strategies , 1999 .

[6]  A. Rubinstein.  Finite automata play the repeated prisoner's dilemma , 1986 .

[7]  Christian Ewerhart,et al.  Chess-like Games Are Dominance Solvable in at Most Two Steps , 2000, Games Econ. Behav..

[8]  Dean P. Foster,et al.  Regret in the On-Line Decision Problem , 1999 .

[9]  A. Rubinstein,et al.  The Structure of Nash Equilibrium in Repeated Games with Finite Automata (Now published in Econometrica, 56 (1988), pp.1259-1282.) , 1986 .

[10]  J. Robinson.  AN ITERATIVE METHOD OF SOLVING A GAME , 1951, Classics in Game Theory.

[11]  L. Shapley,et al.  Potential Games , 1994 .

[12]  Peter Auer,et al.  The Nonstochastic Multiarmed Bandit Problem , 2002, SIAM J. Comput..

[13]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[14]  Elchanan Ben-Porath,et al.  Repeated games with Finite Automata , 1993 .

[15]  A. Neyman.  Bounded complexity justifies cooperation in the finitely repeated prisoners' dilemma , 1985 .

[16]  R. Rosenthal.  A class of games possessing pure-strategy Nash equilibria , 1973 .

[17]  J. Vial,et al.  Strategically zero-sum games: The class of games whose completely mixed equilibria cannot be improved upon , 1978 .

[18]  Christos H. Papadimitriou,et al.  Worst-case equilibria , 1999 .

[19]  James Hannan,et al.  4. APPROXIMATION TO RAYES RISK IN REPEATED PLAY , 1958 .