← Back to all news
arXiv AI By Taozheng Zhu, Shixiong Jiang, Fanxin Kong

Vulnerability Analysis for Safe Multi-Agent Reinforcement

Read the original on arXiv AI →

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.

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 Machine Learning
Sep 14

Robust Policy Optimization via Adversarial Importance Sampling

The paper introduces Adversarial Importance Sampling (Advis), a technique that leverages importance sampling over standard training trajectories to estimate and optimize worst‑case returns without extra environment interactions or auxiliary networks, thereby capturing long‑term robustness. It also presents advrl, a modular PyTorch library that consolidates existing robustness methods and adversarial attacks into single‑file implementations for easier prototyping and reproducible evaluation. Finally, the authors highlight that optimal adversarial hyperparameters do not transfer across agents, prompting evaluation against a broader set of attackers (6–14× more configurations) and demonstrate the effectiveness of their approach on continuous control tasks.

By Amine Andam, Jamal Bentahar, Mustapha Hedabou
agentsreinforcement-learningsafety
More like this →
arXiv Machine Learning
Jul 7

When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPs

arXiv:2604. 10062v3 Announce Type: replace Abstract: We study reward poisoning attacks in reinforcement learning (RL), where an adversary manipulates rewards within constrained budgets to force the target RL agent to adopt a policy that aligns with the attacker's objectives.

By Jose Efraim Aguilar Escamilla, Haoyang Hong, Jiawei Li, Haoyu Zhao, Xuezhou Zhang, Sanghyun Hong, Huazheng Wang
agentsreinforcement-learning
More like this →
arXiv AI
Oct 12

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

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.

By Hongrui Zheng, Aditya Singh, Rahul Mangharam
agentsreinforcement-learningefficiencysafety
More like this →