Learning to Draw: Emergent Communication through Sketching

Daniela Mihai, Jonathon Hare

Keywords: Emergent Communication, Sketching, Drawing, Perceptual Loss, Interpretability, Visual Communication

Abstract: Evidence that visual communication preceded written language and provided a basis for it goes back to prehistory, in forms such as cave and rock paintings depicting traces of our distant ancestors. Emergent communication research has sought to explore how agents can learn to communicate in order to collaboratively solve tasks. Existing research has focused on language, with a learned communication channel transmitting sequences of discrete tokens between the agents. In this work, we explore a visual communication channel between agents that are allowed to draw with simple strokes. Our agents are parameterised by deep neural networks, and the drawing procedure is differentiable, allowing for end-to-end training. In the framework of a referential communication game, we demonstrate that agents can not only successfully learn to communicate by drawing, but with appropriate inductive biases, can do so in a fashion that humans can interpret. We hope to encourage future research to consider visual communication as a more flexible and directly interpretable alternative of training collaborative agents.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We use self-supervised play to train artificial agents to communicate by drawing and then show that with the appropriate inductive bias a human can successfully play the same games with the pretrained drawing agent.

Code: https://github.com/Ddaniela13/LearningToDraw

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/learning-to-draw-emergent-communication/code)