arXiv Machine Learning October 5, 2026 By Jialiang Fan, Shixiong Jiang, Mengyu Liu, Fanxin Kong

Demonstration-Guided Observation Attacks on Black-Box Safe Reinforcement Learning Controllers for Robotic Systems

Read the original on arXiv Machine Learning →

The Flow has not summarised this story yet — read it at arXiv Machine Learning.

arXiv AI

Sep 1

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

arXiv:2402.03741v4 Announce Type: replace-cross Abstract: Recent advancements in multi-agent reinforcement learning (MARL) have opened up vast application prospects, such as swarm control of drones,...

By Oubo Ma, Yuwen Pu, Linkang Du, Yang Dai, Ruo Wang, Xiaolei Liu, Yingcai Wu, Shouling Ji

agents reinforcement-learning robotics safety

arXiv AI

Jun 30

RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learning

arXiv:2606. 29867v1 Announce Type: cross Abstract: Deep Reinforcement Learning (DRL) has achieved significant success in robotics and autonomous systems, yet remains vulnerable to adversarial perturbations that can severely degrade performance.

By Adithya Mohan, Daniel Kriegl, Torsten Sch\"on

agents reinforcement-learning robotics benchmarks safety

arXiv Machine Learning

Aug 4

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks

arXiv:2506. 22423v2 Announce Type: replace Abstract: Unmanned Aerial Vehicles (UAVs) depend on onboard sensors for perception, navigation, and control.

By Pritam Dash, Ethan Chan, Nathan P. Lawrence, Karthik Pattabiraman

reinforcement-learning robotics safety

arXiv Machine Learning

Jul 15

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning

arXiv:2607. 12784v1 Announce Type: cross Abstract: Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation.

By Paolo Magliano, Puze Liu, Jan Peters, Davide Tateo, Raffaello Camoriano

agents reinforcement-learning robotics benchmarks safety

arXiv AI

Jun 16

ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control

arXiv:2606. 16605v1 Announce Type: new Abstract: World models are widely used in robotic and agentic engineering control systems due to their ability to learn latent dynamics for planning and decision-making.

By Junjian Zhang, Hao Tan, Ruonan Li, Dong Zhu, Aiping Li, Zhaoquan Gu

agents robotics benchmarks safety

Hugging Face Trending Papers

Jul 14

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning

Reinforcement Learning has revolutionized the landscape of robotic research, allowing robust learning of complex robotic skills in simulation. However, real-world deployment in open-ended environments requires strong safety guarantees to prevent dangerous or harmful behaviors.

agents reinforcement-learning robotics benchmarks safety

One email a morning, machine-written

Related stories

SUB-PLAY: Adversarial Policies against Partially Observed Multi-Agent Reinforcement Learning Systems

RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement Learning

ARMOR: Robust Reinforcement Learning-based Control for UAVs under Physical Attacks

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning

ARB4WM: An Adversarial Robustness Benchmark for World Models in Continuous Control

Directional Constraints for Efficient Exploration in Safe Reinforcement Learning