Asymmetric multiagent reinforcement learning

Abstract

A novel method for asymmetric multiagent reinforcement learning is introduced in this paper. The method addresses the problem where the information states of the agents involved in the learning task are not equal; some agents (leaders) have information on how their opponents (followers) will select their actions and based on this information leaders encourage followers to select actions that lead to improved payoffs for the leaders. This kind of configuration arises, e.g. in semi-centralized multiagent systems with an external global utility associated to the system. We present a brief literature survey of multiagent reinforcement learning based on Markov games and then construct an asymmetric learning method that utilizes the theory of Markov games. Additionally, we test the proposed method with a simple example application.