外观
论文arXiv 2610.1373719 天前
SafeDiSTL：为安全多智能体强化学习分解联合约束
原文链接：SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning（arXiv 2610.13737 · 发布日期：2026-10-09）
SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
SafeDiSTL针对共享约束下的多智能体安全信用分配，利用STL鲁棒性与可微敏感度分解违规成本，并在运输、导航和交通任务中验证。
核心要点
- 共享目标或集体安全的团队级违规成本，难以区分各智能体动作影响。
- SafeDiSTL用STL鲁棒性度量回合级违规，并以运行最大成本增量表示。
- 结合平滑全回合鲁棒性和可微动力学，按含延迟效应的敏感度分摊成本。
- 运输安全成功率达基线1.6-5.1倍，导航提升11.1%，交通吞吐增50-68%。
验证范围与局限：验证范围为合作载荷运输、连接导航和网络化交通控制任务。
英文摘要 (Abstract)
Cooperative multi-agent tasks often impose constraints on a shared objective or collective safety. A team level violation cost function can measure this constraint outcome, but does not distinguish which agents' actions most strongly influence that violation. We present SafeDiSTL, a constrained multi-agent reinforcement learning framework that allows for credit assignment even with joint constraint measurements. We use Signal Temporal Logic (STL) robustness to measure episode-level violation through running-maximum cost increments. Smooth full-episode robustness and differentiable dynamics provide action sensitivities, which allocate each cost increment across agents at the same decision time. These sensitivities account for delayed effects when weighting agents' shares of each cost increment. We study the framework in cooperative payload transport, connected navigation, and networked traffic control tasks. SafeDiSTL achieves 1.6-5.1x the safe-success rate in transport, improves navigation safe-success by 11.1%, and delivers 50-68% more throughput in traffic when compared to constrained baselines. Results demonstrate a strong improvement of the learned policy in dealing with shared constraint while retaining the performance of unconstrained policies.
作者：Hongrui Zheng, Aditya Singh, Rahul Mangharam
来源
本页事实对应的公开页面，以原文为准。