Control as Probabilistic Inference as an Emergent Communication Mechanism in Multi-Agent Reinforcement Learning

Understand

This paper proposes a generative probabilistic model integrating emergent communication and multi-agent reinforcement learning.

• The agents plan their actions by probabilistic inference, called control as inference, and communicate using messages that are latent variables and estimated based on the planned actions.
• Through these messages, each agent can send information about its actions and know information about the actions of another agent.
• Therefore, the agents change their actions according to the estimated messages to achieve cooperative tasks.