Control As Probabilistic Inference As An Emergent Communication Mechanism In Multi-agent Reinforcement Learning

Abstract

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. This inference of messages can be considered as communication, and this procedure can be formulated by the Metropolis-Hasting naming game. Through experiments in the grid world environment, we show that the proposed PGM can infer meaningful messages to achieve the cooperative task.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keynakamura2023control

Related papers

• Inference-based Deterministic Messaging For Multi-agent Communication (2021)0.00
• Communicating Plans, Not Percepts: Scalable Multi-agent Coordination With Embodied World Models (2025)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Counterfactual Multi-agent Reinforcement Learning With Graph Convolution Communication (2020)0.00
• Probabilistic Recursive Reasoning For Multi-agent Reinforcement Learning (2019)0.00
• Learning Emergent Discrete Message Communication For Cooperative Reinforcement Learning (2021)5.24
• On The Role Of Emergent Communication For Social Learning In Multi-agent Reinforcement Learning (2023)0.00
• Inductive Bias For Emergent Communication In A Continuous Setting (2023)0.00