Evolutionary game dynamics in populations with different learners

We study evolutionary game theory in a setting where individuals learn from each other. We extend the traditional approach by assuming that a population contains individuals with different learning abilities. In particular, we explore the situation where individuals have different search spaces, when attempting to learn the strategies of others. The search space of an individual specifies the set of strategies learnable by that individual. The search space is genetically given and does not change under social evolutionary dynamics. We introduce a general framework and study a specific example in the context of direct reciprocity. For this example, we obtain the counter intuitive result that cooperation can only evolve for intermediate benefit-to-cost ratios, while small and large benefit-to-cost ratios favor defection. Our paper is a step toward making a connection between computational learning theory and evolutionary game dynamics.

► We introduce a general framework of evolutionary game theory where the population consists of different types of learners.
► We study an example of direct reciprocity and show that cooperation can only evolve for intermediate benefit-to-cost ratios.
► We show that in our framework mutation acts to stabilize cooperation.
► Our paper is a step toward making a connection between computational learning theory and evolutionary game dynamics.