Mind model seems necessary for the emergence of communication

TL;DR

This paper investigates how the inclusion of intention modeling in reinforcement learning agents is crucial for the emergence of communication, showing that without it, agents struggle to establish symbol-meaning associations.

Contribution

It demonstrates that modeling the intentions of other agents is essential for effective communication development in reinforcement learning frameworks.

Findings

Intention modeling enables quick symbol-meaning agreement.

Without intention modeling, symbol-meaning association is difficult.

Assuming mutual intention models can sometimes hinder communication.

Abstract

We consider communication when there is no agreement about symbols and meanings. We treat it within the framework of reinforcement learning. We apply different reinforcement learning models in our studies and simplify the problem as much as possible. We show that the modelling of the other agent is insufficient in the simplest possible case, unless the intentions can also be modelled. The model of the agent and its intentions enable quick agreements about symbol-meaning association. We show that when both agents assume an `intention model' about the other agent then the symbol-meaning association process can be spoiled and symbol meaning association may become hard.