Decentralized Safe Multi-Agent Reinforcement Learning via Predictive Shielding

2026-09-07

AI Summary

针对多机器人系统部署时的安全与性能问题，提出了一种结合预测防护和基于模型的有限时间Q学习的去中心化框架。

Abstract

Environments are increasingly populated by multiple robots performing independent tasks with limited prior knowledge of each other. Deploying such multi-agent systems presents significant challenges. Specifically, shifts in deployment states compared to training data can lead to poor policy performance and compromised safety. While safety shields exist to mitigate these risks, they are typically reactive, which degrades performance near unseen obstacles,and centralized, limiting their scalability. To address this, we propose a decentralized framework that integrates predictive shielding with model-based finite horizon Q-learning. This approach allows agents to safely adapt their pre-trained policies during deployment. Furthermore, to mitigate livelocks in symmetric scenarios, we introduce a communication- free protocol for conflict resolution

Problem

• multi-agent systems
• safety shields
• reactive
• centralized
• policy performance

Innovation

• decentralized framework
• predictive shielding
• model-based finite horizon Q-learning
• communication-free protocol