Scalable Communication for Multi-Agent Reinforcement Learning via Transformer-Based Email Mechanism

TL;DR

This paper introduces a scalable Transformer-based email mechanism for multi-agent reinforcement learning that enables efficient, targeted communication among agents, improving cooperation in partially-observed environments without increasing complexity as agent numbers grow.

Contribution

The paper proposes a novel Transformer-based email mechanism that enables scalable, targeted communication in multi-agent reinforcement learning, inspired by human email forwarding.

Findings

TEM outperforms baselines on multiple benchmarks.

TEM maintains performance with varying agent numbers.

TEM does not require retraining when agent count changes.

Abstract

Communication can impressively improve cooperation in multi-agent reinforcement learning (MARL), especially for partially-observed tasks. However, existing works either broadcast the messages leading to information redundancy, or learn targeted communication by modeling all the other agents as targets, which is not scalable when the number of agents varies. In this work, to tackle the scalability problem of MARL communication for partially-observed tasks, we propose a novel framework Transformer-based Email Mechanism (TEM). The agents adopt local communication to send messages only to the ones that can be observed without modeling all the agents. Inspired by human cooperation with email forwarding, we design message chains to forward information to cooperate with the agents outside the observation range. We introduce Transformer to encode and decode the message chain to choose the next receiver selectively. Empirically, TEM outperforms the baselines on multiple cooperative MARL benchmarks. When the number of agents varies, TEM maintains superior performance without further training.