Learning What To Say And How Precisely: Efficient Communication Via Differentiable Discrete Communication Learning

Abstract

Effective communication in multi-agent reinforcement learning (MARL) is critical for success but constrained by bandwidth, yet past approaches have been limited to complex gating mechanisms that only decide \textit\{whether\} to communicate, not \textit\{how precisely\}. Learning to optimize message precision at the bit-level is fundamentally harder, as the required discretization step breaks gradient flow. We address this by generalizing Differentiable Discrete Communication Learning (DDCL), a framework for end-to-end optimization of discrete messages. Our primary contribution is an extension of DDCL to support unbounded signals, transforming it into a universal, plug-and-play layer for any MARL architecture. We verify our approach with three key results. First, through a qualitative analysis in a controlled environment, we demonstrate \textit\{how\} agents learn to dynamically modulate message precision according to the informational needs of the task. Second, we integrate our varian

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keykapoor2025learning

Related papers

• An Analysis Of Discretization Methods For Communication Learning With Multi-agent Reinforcement Learning (2022)0.00
• Learning Emergent Discrete Message Communication For Cooperative Reinforcement Learning (2021)5.24
• An In-depth Analysis Of Discretization Methods For Communication Learning Using Backpropagation With Multi-agent Reinforcement Learning (2023)0.00
• Effective Communications: A Joint Learning And Communication Framework For Multi-agent Reinforcement Learning Over Noisy Channels (2021)0.00
• DACOM: Learning Delay-aware Communication For Multi-agent Reinforcement Learning (2022)0.00
• Provably Efficient Multi-agent Reinforcement Learning With Fully Decentralized Communication (2021)0.00
• On The Role Of Emergent Communication For Social Learning In Multi-agent Reinforcement Learning (2023)0.00
• Rgmcomm: Return Gap Minimization Via Discrete Communications In Multi-agent Reinforcement Learning (2023)6.77