RODE: Learning Roles to Decompose Multi-Agent Tasks

TL;DR

RODE introduces a role-based multi-agent learning framework that decomposes complex tasks by clustering actions according to their environmental effects, enabling scalable learning and rapid transfer to larger environments.

Contribution

It proposes a novel role discovery method using action effect clustering and a bi-level learning hierarchy to improve multi-agent reinforcement learning efficiency and scalability.

Findings

Outperforms state-of-the-art MARL algorithms on most StarCraft II benchmarks.

Achieves rapid transfer to larger environments with more agents.

Enhances learning efficiency through integrated action effect information.

Abstract

Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. However, it is largely unclear how to efficiently discover such a set of roles. To solve this problem, we propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. Learning a role selector based on action effects makes role discovery much easier because it forms a bi-level learning hierarchy -- the role selector searches in a smaller role space and at a lower temporal resolution, while role policies learn in significantly reduced primitive action-observation spaces. We further integrate information about action effects into the role policies to boost learning efficiency and policy generalization. By virtue of these advances, our method (1) outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark and (2) achieves rapid transfer to new environments with three times the number of agents. Demonstrative videos are available at https://sites.google.com/view/rode-marl .