Efficient Communication In Multi-agent Reinforcement Learning Via Variance Based Control

Abstract

Multi-agent reinforcement learning (MARL) has recently received considerable attention due to its applicability to a wide range of real-world applications. However, achieving efficient communication among agents has always been an overarching problem in MARL. In this work, we propose Variance Based Control (VBC), a simple yet efficient technique to improve communication efficiency in MARL. By limiting the variance of the exchanged messages between agents during the training phase, the noisy component in the messages can be eliminated effectively, while the useful part can be preserved and utilized by the agents for better performance. Our evaluation using a challenging set of StarCraft II benchmarks indicates that our method achieves \(2-10\times\) lower in communication overhead than state-of-the-art MARL algorithms, while allowing agents to better collaborate by developing sophisticated strategies.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhang2019efficient

Related papers

• Reducing Variance Caused By Communication In Decentralized Multi-agent Deep Reinforcement Learning (2025)0.00
• Bandwidth-constrained Variational Message Encoding For Cooperative Multi-agent Reinforcement Learning (2025)0.00
• 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
• NVIF: Neighboring Variational Information Flow For Large-scale Cooperative Multi-agent Scenarios (2022)0.00
• MACTAS: Self-attention-based Inter-agent Communication In Multi-agent Reinforcement Learning With Action-value Function Decomposition (2025)0.00
• A Variational Approach To Mutual Information-based Coordination For Multi-agent Reinforcement Learning (2023)0.00
• Distributed Policy Gradient With Variance Reduction In Multi-agent Reinforcement Learning (2021)0.00