# Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances

## TL;DR

This paper investigates how deep network agents develop communication protocols about object affordances, revealing that symmetry alone does not ensure the emergence of a shared language, with agents creating multiple idiolects.

## Contribution

It introduces a new task simulating human-like object affordance understanding and analyzes the conditions for genuine bilateral communication among agents.

## Key findings

- Agents solve the task through referential communication.
- Multiple idiolects emerge among agents.
- Full symmetry does not guarantee a common language.

## Abstract

Recent research studies communication emergence in communities of deep network agents assigned a joint task, hoping to gain insights on human language evolution. We propose here a new task capturing crucial aspects of the human environment, such as natural object affordances, and of human conversation, such as full symmetry among the participants. By conducting a thorough pragmatic and semantic analysis of the emergent protocol, we show that the agents solve the shared task through genuine bilateral, referential communication. However, the agents develop multiple idiolects, which makes us conclude that full symmetry is not a sufficient condition for a common language to emerge.