Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations

Kalesha Bullard, Franziska Meier, Douwe Kiela, Joelle Pineau, Jakob Nicolaus Foerster

Keywords: emergent communication, multi-agent communication, multi-agent reinforcement learning

Abstract:

Effective communication is an important skill for enabling information exchange and cooperation in multi-agent settings. Indeed, emergent communication is now a vibrant field of research, with common settings involving discrete cheap-talk channels. One limitation of this setting is that it does not allow for the emergent protocols to generalize beyond the training partners.
Furthermore, so far emergent communication has primarily focused on the use of symbolic channels. In this work, we extend this line of work to a new modality, by studying agents that learn to communicate via actuating their joints in a 3D environment. We show that under realistic assumptions, a non-uniform distribution of intents and a common-knowledge energy cost, these agents can find protocols that generalize to novel partners. We also explore and analyze specific difficulties associated with finding these solutions in practice. Finally, we propose and evaluate initial training improvements to address these challenges, involving both specific training curricula and providing the latent feature that can be coordinated on during training.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: Initial investigation into the emergence of physical communication protocols for embodied agents (e.g. robots), with analysis on generalization to novel partners.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=63zGAxAkJW