deep-rl-adversarial-vulnerability

IN premise — entries/2026/06/21/wiki-Reinforcement_learning-chunk-5.md

Created 2026-06-21T09:55:53+00:00

Deep RL policies share adversarial features across MDPs (Korkmaz 2022), making adversarial vulnerability a key limitation of deep RL

Dependents

These beliefs depend on this one:

• IN neural-network-adversarial-vulnerability-general — Adversarial vulnerability is a general property of neural networks spanning supervised learning (imperceptible image perturbations), reinforcement learning (shared adversarial features across MDPs), and even single-pixel attacks — not a quirk of any particular architecture or domain.