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

by   Kalesha Bullard, et al.

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.



There are no comments yet.


page 1

page 2

page 3

page 4


Quasi-Equivalence Discovery for Zero-Shot Emergent Communication

Effective communication is an important skill for enabling information e...

A Survey of Multi-Agent Reinforcement Learning with Communication

Communication is an effective mechanism for coordinating the behavior of...

Heterogeneous Graph Attention Networks for Learning Diverse Communication

Multi-agent teaming achieves better performance when there is communicat...

On Emergent Communication in Competitive Multi-Agent Teams

Several recent works have found the emergence of grounded compositional ...

Modelling and Verification of Reconfigurable Multi-Agent Systems

We propose a formalism to model and reason about reconfigurable multi-ag...

Learning to Communicate in a Noisy Environment

In this work we examine the problem of learning to cooperate in the cont...

Active Rendezvous for Multi-Robot Pose Graph Optimization using Sensing over Wi-Fi

We present a novel framework for collaboration amongst a team of robots ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.