Learning to Communicate with Strangers via Channel Randomisation Methods

Research output: Chapter in Book/Report/Conference proceedingConference paperpeer-review

3 Downloads (Pure)


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.
Original languageEnglish
Title of host publicationThe 4th Workshop on Emergent Communication at the International Conference on Neural Information Processing (NeurIPS)
Publication statusPublished - 2020


  • Deep Learning
  • Reinforcement Learning
  • Emergent Communication
  • Domain Generalization
  • Out-Of-Distribution Generalisation
  • Multi-agent Learning
  • Multi-agent reinforcement learning


Dive into the research topics of 'Learning to Communicate with Strangers via Channel Randomisation Methods'. Together they form a unique fingerprint.

Cite this