Learning to Ground Decentralized Multi-Agent Communication with Contrastive Learning
Published in ICLR-22 Emergent Communication Workshop, 2022
Lo, Yat Long and Biswa Sengupta. ICLR Workshop on Emergent Communication . 2022. (Runner-up Best Paper)
Abstract
For communication to happen successfully, a common language is required between agents to understand information communicated by one another. Inducing the emergence of a common language has been a difficult challenge to multiagent learning systems. In this work, we introduce an alternative perspective to the communicative messages sent between agents, considering them as different incomplete views of the environment state. Based on this perspective, we propose a simple approach to induce the emergence of a common language by maximizing the mutual information between messages of a given trajectory in a self-supervised manner. By evaluating our method in communication-essential environments, we empirically show how our method leads to better learning performance and speed, and learns a more consistent common language than existing methods, without introducing additional learning parameters.