Learning to cooperate: Emergent communication in multi-agent navigation
This work addresses the challenge of emergent communication in multi-agent systems, which is incremental as it builds on prior research in language evolution and cooperative AI.
The study tackled the problem of enabling artificial agents to develop communication protocols for cooperative navigation tasks, showing that agents learned interpretable signals that allowed them to efficiently and often optimally solve the tasks, with signals clustering spatially and exhibiting compositional structure.
Emergent communication in artificial agents has been studied to understand language evolution, as well as to develop artificial systems that learn to communicate with humans. We show that agents performing a cooperative navigation task in various gridworld environments learn an interpretable communication protocol that enables them to efficiently, and in many cases, optimally, solve the task. An analysis of the agents' policies reveals that emergent signals spatially cluster the state space, with signals referring to specific locations and spatial directions such as "left", "up", or "upper left room". Using populations of agents, we show that the emergent protocol has basic compositional structure, thus exhibiting a core property of natural language.