Learning Emergent Discrete Message Communication for Cooperative Reinforcement Learning

by   Sheng Li, et al.

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.



page 4

page 6

page 7


Minimizing Communication while Maximizing Performance in Multi-Agent Reinforcement Learning

Inter-agent communication can significantly increase performance in mult...

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

Communication is crucial in multi-agent reinforcement learning when agen...

Learning to Communicate with Strangers via Channel Randomisation Methods

We introduce two methods for improving the performance of agents meeting...

Distributed Mechanism Design for Multicast Transmission

In the standard Mechanism Design framework (Hurwicz-Reiter), there is a ...

Incentivizing the Emergence of Grounded Discrete Communication Between General Agents

We converted the recently developed BabyAI grid world platform to a send...

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

Previous work has shown that artificial neural agents naturally develop ...

Detection under One-Bit Messaging over Adaptive Networks

This work studies the operation of multi-agent networks engaged in binar...
This week in AI

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