Admissable: Training Reinforcement Learning Agents against Adversarial Missingness

2026-09-14

AI Summary

本文针对强化学习中对抗性特征缺失问题，提出了一种对抗训练算法，并在三个MuJoCo基准环境中证明了其有效性，提高了鲁棒性。

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.

Problem

• Reinforcement Learning
• Adversarial Missingness
• Robustness

Innovation

• Adversarial Missingness
• Reinforcement Learning
• Robustness
• MuJoCo