Feudal Multi-Agent Hierarchies for Cooperative Reinforcement Learning

TL;DR

This paper introduces Feudal Multi-agent Hierarchies (FMH), a hierarchical framework where a manager agent communicates subgoals to worker agents, improving cooperative learning and scalability in reinforcement learning tasks.

Contribution

The paper presents FMH, a novel hierarchical structure for multi-agent reinforcement learning that enhances cooperation and scalability through subgoal communication.

Findings

FMH outperforms flat cooperative methods with shared rewards.

FMH scales better with increasing number of agents.

Hierarchical communication improves learning efficiency.

Abstract

We investigate how reinforcement learning agents can learn to cooperate. Drawing inspiration from human societies, in which successful coordination of many individuals is often facilitated by hierarchical organisation, we introduce Feudal Multi-agent Hierarchies (FMH). In this framework, a 'manager' agent, which is tasked with maximising the environmentally-determined reward function, learns to communicate subgoals to multiple, simultaneously-operating, 'worker' agents. Workers, which are rewarded for achieving managerial subgoals, take concurrent actions in the world. We outline the structure of FMH and demonstrate its potential for decentralised learning and control. We find that, given an adequate set of subgoals from which to choose, FMH performs, and particularly scales, substantially better than cooperative approaches that use a shared reward function.