IFISC


UIB CSIC

MPIPKS


MAx Planck
Stochastic learning in game theory
Tobias Galla
University of Manchester, UK

I will discuss the learning dynamics of a small set of players who interact repeatedly in a given game, and who learn from past experience adapting to their opponents' actions. Such dynamics lead to to modified replicator equations in a deterministic limit, corresponding to an infinite number of observations made between adaption events. If only a finite number of moves of the opposing players are sampled between adaption steps, the learning dynamics becomes stochastic, similar to noise corrections observed in evolutionary systems in finite populations. I will here discuss the effects of memory-loss and of noise on the learning of agents for some simple two-player games, and show that the combination of both may affect the attractors considerably. Memory-loss may promote co-operation in social dilemmas, and the agents fail to retrieve the Nash equilibrium. In cyclic games, memory-loss drives the system towards stability in deterministic learning, but fixed points may be removed if sampling is stochastic, resulting in coherent random cycling.


Back
Este texto no debe aparecer en nigún sitio ni se debe poder copiar etc, pero eso va a ser dificil de conseguir, lo sé, y además debe ser un texto largo para que ocupe más de una linea y funcione el diseño.