Learning to Communicate with Deep Multi-Agent Reinforcement Learning

TL;DR

This paper introduces deep multi-agent reinforcement learning methods for agents to learn communication protocols in complex environments, enabling improved cooperation through end-to-end learning.

Contribution

It proposes two novel approaches, RIAL and DIAL, for learning communication protocols with deep neural networks, including a differentiable method allowing backpropagation through communication channels.

Findings

Successful learning of communication protocols in complex environments

Introduction of new environments for studying multi-agent communication

Engineering innovations crucial for training deep multi-agent systems

Abstract

We consider the problem of multiple agents sensing and acting in environments with the goal of maximising their shared utility. In these environments, agents must learn communication protocols in order to share information that is needed to solve the tasks. By embracing deep neural networks, we are able to demonstrate end-to-end learning of protocols in complex environments inspired by communication riddles and multi-agent computer vision problems with partial observability. We propose two approaches for learning in these domains: Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL). The former uses deep Q-learning, while the latter exploits the fact that, during learning, agents can backpropagate error derivatives through (noisy) communication channels. Hence, this approach uses centralised learning but decentralised execution. Our experiments introduce new environments for studying the learning of communication protocols and present a set of engineering innovations that are essential for success in these domains.