SOURCE-LINKED INTELLIGENCE
SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning
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 pro
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-09T15:32:06.000Z
First collected: 2026-10-13T16:12:24.076Z. This is not the publication date.