Choice without beliefs

This paper provides an axiomatic foundation for decision making in complex settings in which the decision maker does not have complete structural knowledge of the environment. The agent knows the set of actions he can take, he formulates preferences directly on the actions, and chooses according to these preferences. On the basis of experience he modifies these preferences according to a systematic procedure. A group of natural structural restrictions and a group of independence axioms are imposed on this procedure. The main result is an axiomatic foundation for a set of simple adaptive learning procedures which include the replicator dynamic.

[1]  Jonathan Barzilai,et al.  On the foundations of measurement , 2001, 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat.No.01CH37236).

[2]  J. Aczél,et al.  Lectures on Functional Equations and Their Applications , 1968 .

[3]  Dana Heller.  Parametric Adaptive Learning , 2000 .

[4]  W. Hildenbrand.  Core and Equilibria of a Large Economy. , 1974 .

[5]  S. Modica,et al.  Awareness and partitional information structures , 1994 .

[6]  F. J. Anscombe,et al.  A Definition of Subjective Probability , 1963 .

[7]  Barton L. Lipman,et al.  Standard state-space models preclude unawareness , 1998 .

[8]  K. Schlag.  Why Imitate, and If So, How?, : A Boundedly Rational Approach to Multi-armed Bandits , 1998 .

[9]  A. Rustichini,et al.  RULES OF THUMB AND DYNAMICPROGRAMMING , 1995 .

[10]  D. Fudenberg,et al.  Consistency and Cautious Fictitious Play , 1995 .

[11]  J. Cross.  A theory of adaptive economic behavior , 1983 .

[12]  L. Samuelson,et al.  Evolutionary Stability in Asymmetric Games , 1992 .

[13]  E. Rowland.  Theory of Games and Economic Behavior , 1946, Nature.

[14]  A. Rustichini.  Optimal Properties of Stimulus-Response Learning Models* , 1999 .

[15]  Tilman Börgers,et al.  Learning Through Reinforcement and Replicator Dynamics , 1997 .

[16]  S. Modica,et al.  Unawareness: A Formal Theory of Unforeseen Contingencies. Part I , 1993 .

[17]  W. Arthur.  Designing Economic Agents that Act Like Human Agents: A Behavioral Approach to Bounded Rationality , 1991 .

[18]  J. Weibull.  What have we learned from Evolutionary Game Theory so far , 1998 .

[19]  W. Brian Arthur,et al.  On designing economic agents that behave like human agents , 1993 .

[20]  Jaap Van Brakel,et al.  Foundations of measurement , 1983 .

[21]  A. Marcet,et al.  Recurrent Hyperinflations and Learning , 2003 .

[22]  H. Uhlig,et al.  Rules of Thumb versus Dynamic Programming , 1999 .