Games of Stochastic Automata

Abstract

The collective behavior of variable-structure stochastic automata in competitive game situations is investigated. It is demonstrated that when the automata use optimal or ?-optimal reinforcement schemes, the Von Neumann value is achieved for games against nature as well as for two-player zero-sum games having a saddle point. Computer simulations of the latter games also indicate that in the absenice of a saddle point the value of the game oscillates about the Von Neunmann value in mixed strategies.