English

Learning to Communicate with Strangers via Channel Randomisation Methods

Machine Learning 2021-04-21 v1 Artificial Intelligence Computation and Language

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.

Keywords

Cite

@article{arxiv.2104.09557,
  title  = {Learning to Communicate with Strangers via Channel Randomisation Methods},
  author = {Dylan Cope and Nandi Schoots},
  journal= {arXiv preprint arXiv:2104.09557},
  year   = {2021}
}
R2 v1 2026-06-24T01:20:44.399Z