Computational Modeling Lab
|
Abstract:
como.vub.ac.be Abstract. In this talk we tackle learning and adaptiveness in MultiAgent Systems from an Evolutionary Game Theoretic perspective. Modeling learning agents in the context of Multi-agent Systems requires an adequate understanding of their dynamic behaviour. Therefore we revise Evolutionary Game Theory. Evolutionary Game Theory provides a dynamics which describes how strategies evolve over time. Borgers et al. [1] and Tuyls et al. [11] have shown how classical Reinforcement Learning techniques such as Crosslearning and Q-learning relate to the Replicator Dynamics. This provides a better understanding of the learning process. However, we believe Evolutionary Game Theory can do more. In [12] we introduced an extension of the Replicator Dynamics from Evolutionary Game Theory. Based on this new dynamics, a Reinforcement Learning algorithm was developed that attains an evolutionary stable equilibrium for all types of games.
Citations
No citations identified.
