An adversarial training algorithm is developed and shown to be effectiveness in increasing robustness against adversarial missingness on three MuJoCo benchmark environments and achieves better robustness on all three tasks.
Abstract
In order to make Reinforcement Learning algorithms applicable in real world scenarios, safety must be ensured even under adverse operating conditions. In this work, we consider the challenge of adversarial feature missingness: a scenario in which an adversary occludes features from the agent's observation in order to reduce performance as much as possible. We formally define adversarial missingness for Reinforcement Learning and compare it to the related concepts of $\ell_\infty$-norm bounded adversarial perturbations and learning with missing data. We develop an adversarial training algorithm and show its effectiveness in increasing robustness against adversarial missingness on three MuJoCo benchmark environments. Compared to a baseline trained with random uniform missingness, our method achieves better robustness on all three tasks.
This work introduces Adversarial Importance Sampling (Advis), a method that uses importance sampling over trajectories from standard training to estimate and optimize verifiable worst-case returns and introduces advrl, a modular PyTorch library that provides clean, single-file implementations of existing robustness met...
Amine Andam, Jamal Bentahar, M. Hedabou· 0 citations
Observation uncertainty can drive a deep reinforcement learning (DRL) controller to select inappropriate actions even when its nominal policy performs well. This issue is especially pronounced in robotic systems deployed outside controlled laboratory conditions, where sensing and communication are affected by noise, bi...
Hai-Tao Zhang, Cheng-Yu Liu, Qing-Kai Meng et al.· 2026 3rd International Confe...· 0 citations
RL-FAT is proposed, a reinforcement-learning-inspired fair adversarial training framework that uses policy-gradient based feedback from adversarial predictions to improve adversarial robustness while promoting a more balanced robustness distribution across classes.
This work proposes a unified framework, RACER (Risk-sensitive robust Adversarial critic ConsistEncy-regularized Reinforcement learning), that revisits adversarial RL from a risk-sensitive perspective and introduces a state-dependent adversarial objective that adaptively regulates perturbation strength.
Jia-Xin Wu, Tian-Tian Zhang, Yu-Xing Wang et al.· 0 citations
This work proposes a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model, and shows the success of reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial...
F. Krone, Elena Hoemann, Sven Hallerbach· 0 citations
Adversarial training is one of the most reliable defenses against adversarial attacks, but its high computational cost must generally be paid anew for each task. Robust foundation models offer a promising alternative: adversarially pretrain a model once and then transfer its robustness to downstream tasks through light...
Soichiro Kumano· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 6, 2026
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
