Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition

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

22 Downloads (Pure)


In Emergent Communication (EC) agents learn to communicate with one another, but the protocols that they develop are specialised to their training community. This observation led to research into Zero-Shot Coordination (ZSC) for learning communication strategies that are robust to agents not encountered during training. However, ZSC typically assumes that no prior data is available about the agents that will be encountered in the zero-shot setting. In many cases, this presents an unnecessarily hard problem and rules out communication via preestablished conventions. We propose a novel AI challenge called a Cooperative Language Acquisition Problem (CLAP) in which the ZSC assumptions are relaxed by allowing a 'joiner' agent to learn from a dataset of interactions between agents in a target community. We propose and compare two methods for solving CLAPs: Imitation Learning (IL), and Emergent Communication pretraining and Translation Learning (ECTL), in which an agent is trained in self-play with EC and then learns from the data to translate between the emergent protocol and the target community's protocol.
Original languageEnglish
Title of host publicationProceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI-24)
Publication statusAccepted/In press - 16 Mar 2024


  • cs.LG
  • cs.CL
  • cs.MA


Dive into the research topics of 'Learning Translations: Emergent Communication Pretraining for Cooperative Language Acquisition'. Together they form a unique fingerprint.

Cite this