Learning to Communicate: A Machine Learning Framework for Heterogeneous Multi-Agent Robotic Systems

TL;DR

This paper introduces a reinforcement learning framework enabling multi-agent robotic systems to learn optimal actions and efficient visual communication encoding, facilitating collaboration under resource constraints in complex environments.

Contribution

It proposes a novel actor-encoder architecture that jointly learns control policies and visual communication encoding in multi-agent systems.

Findings

Effective in 3D simulation with realistic visual data

Enables agents to share high-dimensional observations efficiently

Demonstrates improved collaboration performance

Abstract

We present a machine learning framework for multi-agent systems to learn both the optimal policy for maximizing the rewards and the encoding of the high dimensional visual observation. The encoding is useful for sharing local visual observations with other agents under communication resource constraints. The actor-encoder encodes the raw images and chooses an action based on local observations and messages sent by the other agents. The machine learning agent generates not only an actuator command to the physical device, but also a communication message to the other agents. We formulate a reinforcement learning problem, which extends the action space to consider the communication action as well. The feasibility of the reinforcement learning framework is demonstrated using a 3D simulation environment with two collaborating agents. The environment provides realistic visual observations to be used and shared between the two agents.