Complex Systems

Which Types of Learning Make a Simple Game Complex? Download PDF

Shohei Hidaka*
Takuma Torii
Akira Masumi
School of Knowledge Science
Japan Advanced Institute of Science and Technology
1-1 Asahidai, Nomi, Ishikawa, Japan 923-1292
*shhidaka@jaist.ac.jp

Abstract

The present study focuses on a class of games with reinforcement-learning agents that adaptively choose their actions to locally maximize their rewards. By analyzing a limit model with a special type of learning, previous studies suggested that dynamics of games with learners may become chaotic. We evaluated the generality of this model by analyzing the consistency of this limit model in comparison with two other approaches, agent-based simulation and the Markov process model. Our analysis showed inconsistency between the limit model and two other models with more general reinforcement learning. This suggests that reinforcement learning does not lead to complex dynamics in games with learners.