SOURCE-LINKED INTELLIGENCE

A Unified and Constrained View of Regularization-Based Robust Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Regularization-based methods have become a standard approach for training Deep Reinforcement Learning policies against adversarial input perturbations. In this paper, we unify these methods by deriving new upper bounds on the performance gap between the nominal and worst-case policies. Each upper bound is expressed as an existing regularization objective plus a KL-divergence penalty between the nominal and worst-case policies, which further explains why adding a KL penalty improves robustness in practice. Building on these bounds, we formulate robust training as a constrained optimization prob

Read original source ↗ Open in workspace

recordType

paper

region

Global