← Back to all news
arXiv AI By Hongrui Zheng, Aditya Singh, Rahul Mangharam

SafeDiSTL: Decomposing Joint Constraints for Safe Multi-Agent Reinforcement Learning

Read the original on arXiv AI →

SafeDiSTL is a constrained multi‑agent reinforcement learning framework that decomposes joint constraints using Signal Temporal Logic robustness to assign credit to individual agents. By measuring episode‑level violations through running‑maximum cost increments and computing action sensitivities, the method distributes each cost increment among agents at the same decision time, accounting for delayed effects. Experiments on cooperative payload transport, connected navigation, and networked traffic control show that SafeDiSTL improves safe‑success rates and throughput compared to constrained baselines while preserving unconstrained policy performance.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
1d ago

Vulnerability Analysis for Safe Multi-Agent Reinforcement

The paper examines inference‑time observation attacks on Safe Multi‑Agent Reinforcement Learning (SMARL), where an adversary perturbs observations of some agents to alter their actions. It introduces the MinMax Attack framework, which jointly selects adversarial target actions for compromised agents while considering the cooperative resistance of benign agents. The authors derive a bound on the induced safety cost and show through experiments that MinMax Attack causes higher safety costs than existing baselines while maintaining task reward, thus improving attack effectiveness and stealthiness.

By Taozheng Zhu, Shixiong Jiang, Fanxin Kong
agentsreinforcement-learningbenchmarkssafety
More like this →
arXiv Machine Learning
Jun 15

Contract-Based Compositional Shielding for Safe Multi-Agent Reinforcement Learning

arXiv:2606. 14130v1 Announce Type: new Abstract: Safe coordination problems surface in multi-agent reinforcement learning when global safety cannot be enforced by any agent unilaterally: the admissibility of one agent's action may depend on the dynamics of other agents.

By Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli
agentsreinforcement-learningsafety
More like this →
arXiv AI
Jun 2

Coordination Graphs for Constrained Multi-Agent Reinforcement Learning

arXiv:2606. 02337v1 Announce Type: new Abstract: Constrained Multi-agent reinforcement learning (CMARL) faces two intertwined challenges: the joint action space grows exponentially with the number of agents, and additional requirements couple agents in ways that reward structure alone does not capture.

By Santiago Amaya-Corredor, Miguel Calvo-Fullana, Anders Jonsson
agentsreinforcement-learning
More like this →