Learning to Communicate with Strangers via Channel Randomisation Methods

TL;DR

This paper proposes channel randomisation methods, including message mutation and channel permutation, to enhance zero-shot communication performance of agents in first-time interactions, demonstrating positive effects in a simple game setting.

Contribution

Introduces two novel channel randomisation techniques to improve agents' zero-shot communication abilities in first-time interactions.

Findings

Both message mutation and channel permutation improve zero-shot communication performance.

Agents trained with these methods perform better when matched with strangers.

The methods positively influence communication success in a simple two-player game.

Abstract

We introduce two methods for improving the performance of agents meeting for the first time to accomplish a communicative task. The methods are: (1) `message mutation' during the generation of the communication protocol; and (2) random permutations of the communication channel. These proposals are tested using a simple two-player game involving a `teacher' who generates a communication protocol and sends a message, and a `student' who interprets the message. After training multiple agents via self-play we analyse the performance of these agents when they are matched with a stranger, i.e. their zero-shot communication performance. We find that both message mutation and channel permutation positively influence performance, and we discuss their effects.