Non-reciprocating Sharing Methods in Cooperative Q-Learning Environments

Abstract

Past research on multi-agent simulation with cooperative reinforcement learning (RL) focuses on developing sharing strategies that are adopted and used by all agents in the environment. In this paper, we target situations where this assumption of a single sharing strategy that is employed by all agents is not valid. We seek to address how agents with no predetermined sharing partners can exploit groups of cooperatively learning agents to improve learning performance when compared to Independent learning. Specifically, we propose 3 intra-agent methods that do not assume a reciprocating sharing relationship and leverage the pre-existing agent interface associated with Q-Learning to expedite learning.