Coordination-driven learning in multi-agent problem spaces

TL;DR

This paper introduces a new way to measure and optimize coordination among agents in multi-agent reinforcement learning, with implications for adversary-aware RL.

Contribution

It proposes a novel coordination measure and explores its use in optimizing multi-agent policies, advancing the understanding of coordinated learning.

Findings

New coordination metric for multi-agent systems

Implications for adversary-aware reinforcement learning

Enhanced policy optimization through coordination measures

Abstract

We discuss the role of coordination as a direct learning objective in multi-agent reinforcement learning (MARL) domains. To this end, we present a novel means of quantifying coordination in multi-agent systems, and discuss the implications of using such a measure to optimize coordinated agent policies. This concept has important implications for adversary-aware RL, which we take to be a sub-domain of multi-agent learning.