Multi-Agent Curricula and Emergent Implicit Signaling

Emergent communication has made strides towards learning communication from scratch, but has focused primarily on protocols that resemble human language. In nature, multi-agent cooperation gives rise to a wide range of communication that varies in structure and complexity. In this work, we recognize the full spectrum of communication that exists in nature and propose studying lower-level communication. Speci�cally, we study emergent implicit signaling in the context of decentralized multi-agent learning in di�cult, sparse reward environments. However, learning to coordinate in such environments is challenging. We propose a curriculum-driven strategy that combines: (i) velocity-based environment shaping, tailored to the skill level of the multi-agent team; and (ii) a behavioral curriculum that helps agents learn successful single-agent behaviors as a precursor to learning multi-agent behaviors. Pursuitevasion experiments show that our approach learns e�ective coordination, signi�cantly outperforming sophisticated analytical and learned policies. Our method completes the pursuit-evasion task even when pursuers move at half of the evader’s speed, whereas the highest-performing baseline fails at 80% of the evader’s speed. Moreover, we examine the use of implicit signals in coordination through position-based social in�uence. We show that pursuers trained with our strategy exchange more than twice as much information (in bits) than baseline methods, indicating that our method has learned, and relies heavily on, the exchange of implicit signals.

Authors

• Niko A. Grupen
• Daniel D. Lee
• Bart Selman

Keywords

• Multi-Agent Systems
• Reinforcement Learning
• Communication