EAQR: A multiagent Q-learning algorithm for coordination of multiple agents

Abstract

We propose a cooperative multiagent Q-learning algorithm called exploring actions according to Q-value ratios (EAQR). Our aim is to design a multiagent reinforcement learning algorithm for cooperative tasks where multiple agents need to coordinate their behavior to achieve the best system performance. In EAQR, Q-value represents the probability of getting the maximal reward, while each action is selected according to the ratio of its Q-value to the sum of all actions' Q-value and the exploration rate ε. Seven cooperative repeated games are used as cases to study the dynamics of EAQR. Theoretical analyses show that in some cases the optimal joint strategies correspond to the stable critical points of EAQR. Moreover, comparison experiments on stochastic games with finite steps are conducted. One is the box-pushing, and the other is the distributed sensor network problem. Experimental results show that EAQR outperforms the other algorithms in the box-pushing problem and achieves the theoretical optimal performance in the distributed sensor network problem.