Reducing Variance Caused By Communication In Decentralized Multi-agent Deep Reinforcement Learning
2025 · Changxi Zhu, Mehdi Dastani, Shihan Wang
Abstract
In decentralized multi-agent deep reinforcement learning (MADRL), communication can help agents to gain a better understanding of the environment to better coordinate their behaviors. Nevertheless, communication may involve uncertainty, which potentially introduces variance to the learning of decentralized agents. In this paper, we focus on a specific decentralized MADRL setting with communication and conduct a theoretical analysis to study the variance that is caused by communication in policy gradients. We propose modular techniques to reduce the variance in policy gradients during training. We adopt our modular techniques into two existing algorithms for decentralized MADRL with communication and evaluate them on multiple tasks in the StarCraft Multi-Agent Challenge and Traffic Junction domains. The results show that decentralized MADRL communication methods extended with our proposed techniques not only achieve high-performing agents but also reduce variance in policy gradients dur
Authors
(none)
Tags
Stats
Related papers
- Efficient Communication In Multi-agent Reinforcement Learning Via Variance Based Control (2019)0.00
- A Survey Of Multi-agent Deep Reinforcement Learning With Communication (2022)0.00
- Provably Efficient Multi-agent Reinforcement Learning With Fully Decentralized Communication (2021)0.00
- Robust Multi-agent Communication Based On Decentralization-oriented Adversarial Training (2025)0.00
- Distributed Policy Gradient With Variance Reduction In Multi-agent Reinforcement Learning (2021)0.00
- Improving Coordination In Small-scale Multi-agent Deep Reinforcement Learning Through Memory-driven Communication (2019)12.25
- Contextual Knowledge Sharing In Multi-agent Reinforcement Learning With Decentralized Communication And Coordination (2025)0.00
- Cooperative Multi-agent RL With Communication Constraints (2026)0.00