Inference-based Deterministic Messaging For Multi-agent Communication

Abstract

Communication is essential for coordination among humans and animals. Therefore, with the introduction of intelligent agents into the world, agent-to-agent and agent-to-human communication becomes necessary. In this paper, we first study learning in matrix-based signaling games to empirically show that decentralized methods can converge to a suboptimal policy. We then propose a modification to the messaging policy, in which the sender deterministically chooses the best message that helps the receiver to infer the sender's observation. Using this modification, we see, empirically, that the agents converge to the optimal policy in nearly all the runs. We then apply this method to a partially observable gridworld environment which requires cooperation between two agents and show that, with appropriate approximation methods, the proposed sender modification can enhance existing decentralized training methods for more complex domains as well.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybhatt2021inference

Related papers

• Control As Probabilistic Inference As An Emergent Communication Mechanism In Multi-agent Reinforcement Learning (2023)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Multi-agent Curricula And Emergent Implicit Signaling (2021)0.00
• Learning Individually Inferred Communication For Multi-agent Cooperation (2020)0.00
• Multi-agent Reinforcement Learning With Communication-constrained Priors (2025)0.00
• Learning Emergent Discrete Message Communication For Cooperative Reinforcement Learning (2021)5.24
• Scalability Of Message Encoding Techniques For Continuous Communication Learned With Multi-agent Reinforcement Learning (2023)0.00
• Low-bandwidth Communication Emerges Naturally In Multi-agent Learning Systems (2020)0.00