Intelligent Minority Game with genetic-crossover strategies

Abstract

We develop a game theoretical model of $N$ heterogeneous interacting agents called the intelligent minority game. The ``intelligent'' agents play the basic minority game and depending on their performances, generate new strategies using the one-point genetic crossover mechanism. The performances change dramatically and the game moves rapidly to an efficient state (fluctuations in the number of agents performing a particular action, characterized by $\sigma^2$, reaches a low value). There is no ``phase transition'' when we vary $\sigma^2/N$ with $2^M/N$, where $M$ is the ``memory''of an agent.