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

Paper recorded by Signals 4 on 2026-09-11 in cs.LG. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-11 on arXiv · recorded by Signals 4 on 2026-09-14

Category: cs.LG · 机器学习 · first seen 2026-09-14

Abstract

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 no

Read on arXiv →