Cheap Talk Discovery And Utilization In Multi-agent Reinforcement Learning

Abstract

By enabling agents to communicate, recent cooperative multi-agent reinforcement learning (MARL) methods have demonstrated better task performance and more coordinated behavior. Most existing approaches facilitate inter-agent communication by allowing agents to send messages to each other through free communication channels, i.e., cheap talk channels. Current methods require these channels to be constantly accessible and known to the agents a priori. In this work, we lift these requirements such that the agents must discover the cheap talk channels and learn how to use them. Hence, the problem has two main parts: cheap talk discovery (CTD) and cheap talk utilization (CTU). We introduce a novel conceptual framework for both parts and develop a new algorithm based on mutual information maximization that outperforms existing algorithms in CTD/CTU settings. We also release a novel benchmark suite to stimulate future research in CTD/CTU.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keylo2023cheap

Related papers

• AC2C: Adaptively Controlled Two-hop Communication For Multi-agent Reinforcement Learning (2023)0.00
• Context-aware Communication For Multi-agent Reinforcement Learning (2023)3.14
• MACTAS: Self-attention-based Inter-agent Communication In Multi-agent Reinforcement Learning With Action-value Function Decomposition (2025)0.00
• Tacit Learning With Adaptive Information Selection For Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• An Initial Introduction To Cooperative Multi-agent Reinforcement Learning (2024)0.00
• Succinct And Robust Multi-agent Communication With Temporal Message Control (2020)0.00
• Contextual Knowledge Sharing In Multi-agent Reinforcement Learning With Decentralized Communication And Coordination (2025)0.00