Biases for Emergent Communication in Multi-agent Reinforcement Learning

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,...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-12
Main Authors: Eccles, Tom, Bachrach, Yoram, Lever, Guy, Lazaridou, Angeliki, Graepel, Thore
Format: Article
Language:English
Subjects:
Communication
Domains
Human communication
Learning
Multiagent systems
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 communication protocols.
ISSN:2331-8422