Learning to Draw: Emergent Communication through Sketching

Mihai, Daniela and Hare, Jonathon (2021) Learning to Draw: Emergent Communication through Sketching. In Advances in Neural Information Processing Systems 34. vol. 34, Neural Information Processing Systems Foundation. 29 pp .

Record type: Conference or Workshop Item (Paper)

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.

Text

2106.02067 - Version of Record

Restricted to Repository staff only

Request a copy