Learning to Draw: Emergent Communication through Sketching
This work addresses the challenge of developing more flexible and interpretable communication methods for collaborative AI agents, offering a novel alternative to traditional language-based approaches.
The paper tackles the problem of enabling agents to communicate visually through drawing in a referential game, demonstrating that agents can learn to draw interpretable sketches and achieve successful communication with human-interpretable results.
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.