Cooperative Multi-agent Learning in a Large Dynamic Environment

摘要

In this work, we are addressing the problem of cooperative multi-agent learning for distributed decision making in non stationary environments. Our principal focus is to improve learning by exchanging information between local neighbors (agents) and to ensure the adaption to the new environmental form without ignoring knowledge already acquired. First, a distributed dynamic correlation matrix based on multi-Q learning method, presented in [1], is evaluated. To overcome the shortcomings of this method, a new multi-agent reinforcement learning approach and a new cooperative action selection strategy are developed. Several simulation tests are conducted using a cooperative foraging task with a single moving target and show the efficiency of the proposed methods in the case of large, unknown and temporary dynamic environments.