Admissable：训练强化学习智能体以应对对抗性特征缺失
Admissable: Training Reinforcement Learning Agents against Adversarial Missingness
浏览论文内容
中文总结 AI 辅助
针对强化学习中的对抗性特征缺失问题，提出对抗训练算法，在MuJoCo三个基准环境上相比随机缺失基线显著提升鲁棒性。
中文摘要 AI 辅助
为了使强化学习算法能够在现实世界场景中应用，即使在不利的操作条件下也必须确保安全性。在这项工作中，我们考虑了对抗性特征缺失的挑战：即对手从智能体的观测中遮挡特征以尽可能降低性能的场景。我们正式定义了强化学习中的对抗性缺失，并将其与$\u2113_\u221e$范数有界对抗扰动和缺失数据学习等相关概念进行了比较。我们开发了一种对抗训练算法，并在三个MuJoCo基准环境中展示了其在提高对抗性缺失鲁棒性方面的有效性。与使用随机均匀缺失训练的基线相比，我们的方法在所有三个任务上都实现了更好的鲁棒性。
英文摘要
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.
发表机构
- Bielefeld University（比勒费尔德大学）
机构由 AI 辅助整理，请以论文原文为准。
