Learning to Share in Multi-Agent Reinforcement Learning

TL;DR

This paper introduces LToS, a hierarchical decentralized framework for multi-agent reinforcement learning that enables agents to dynamically share rewards, promoting cooperation and improving performance in networked scenarios.

Contribution

The paper proposes a novel bi-level hierarchical framework, LToS, allowing agents to learn reward sharing strategies to enhance cooperation in networked MARL.

Findings

LToS outperforms existing methods in social dilemma scenarios.

LToS improves cooperation and global objective optimization.

The framework is effective across different network scales.

Abstract

In this paper, we study the problem of networked multi-agent reinforcement learning (MARL), where a number of agents are deployed as a partially connected network and each interacts only with nearby agents. Networked MARL requires all agents to make decisions in a decentralized manner to optimize a global objective with restricted communication between neighbors over the network. Inspired by the fact that sharing plays a key role in human's learning of cooperation, we propose LToS, a hierarchically decentralized MARL framework that enables agents to learn to dynamically share reward with neighbors so as to encourage agents to cooperate on the global objective through collectives. For each agent, the high-level policy learns how to share reward with neighbors to decompose the global objective, while the low-level policy learns to optimize the local objective induced by the high-level policies in the neighborhood. The two policies form a bi-level optimization and learn alternately. We empirically demonstrate that LToS outperforms existing methods in both social dilemma and networked MARL scenarios across scales.