NIPS Proceedingsβ

Biases for Emergent Communication in Multi-agent Reinforcement Learning

Part of: Advances in Neural Information Processing Systems 32 (NIPS 2019)

[PDF] [BibTeX] [Supplemental] [Reviews] [Author Feedback] [Meta Review]

Authors

Conference Event Type: Poster

Abstract

We study the problem of emergent communication, in which language arises because speakers and listeners must communicate information in order to solve tasks. In temporally extended reinforcement learning domains, it has proved hard to learn such communication without centralized training of agents, due in part to a difficult joint exploration problem. We introduce inductive biases for positive signalling and positive listening, which ease this problem. In a simple one-step environment, we demonstrate how these biases ease the learning problem. We also apply our methods to a more extended environment, showing that agents with these inductive biases achieve better performance, and analyse the resulting communications protocols.