Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning

02/24/2021
by   Sheng Li, et al.
0

Communication is a important factor that enables agents work cooperatively in multi-agent reinforcement learning (MARL). Most previous work uses continuous message communication whose high representational capacity comes at the expense of interpretability. Allowing agents to learn their own discrete message communication protocol emerged from a variety of domains can increase the interpretability for human designers and other agents.This paper proposes a method to generate discrete messages analogous to human languages, and achieve communication by a broadcast-and-listen mechanism based on self-attention. We show that discrete message communication has performance comparable to continuous message communication but with much a much smaller vocabulary size.Furthermore, we propose an approach that allows humans to interactively send discrete messages to agents.

READ FULL TEXT

page 4

page 6

page 7

research
08/09/2023

Scalability of Message Encoding Techniques for Continuous Communication Learned with Multi-Agent Reinforcement Learning

Many multi-agent systems require inter-agent communication to properly a...
research
11/04/2022

Emergent Quantized Communication

The field of emergent communication aims to understand the characteristi...
research
08/09/2023

An In-Depth Analysis of Discretization Methods for Communication Learning using Backpropagation with Multi-Agent Reinforcement Learning

Communication is crucial in multi-agent reinforcement learning when agen...
research
04/12/2022

An Analysis of Discretization Methods for Communication Learning with Multi-Agent Reinforcement Learning

Communication is crucial in multi-agent reinforcement learning when agen...
research
04/19/2021

Learning to Communicate with Strangers via Channel Randomisation Methods

We introduce two methods for improving the performance of agents meeting...
research
10/05/2020

"LazImpa": Lazy and Impatient neural agents learn to communicate efficiently

Previous work has shown that artificial neural agents naturally develop ...
research
06/30/2022

Towards Human-Agent Communication via the Information Bottleneck Principle

Emergent communication research often focuses on optimizing task-specifi...

Please sign up or login with your details

Forgot password? Click here to reset