Adversarial Style Transfer For Robust Policy Optimization In Deep Reinforcement Learning

Abstract

This paper proposes an algorithm that aims to improve generalization for reinforcement learning agents by removing overfitting to confounding features. Our approach consists of a max-min game theoretic objective. A generator transfers the style of observation during reinforcement learning. An additional goal of the generator is to perturb the observation, which maximizes the agent's probability of taking a different action. In contrast, a policy network updates its parameters to minimize the effect of such perturbations, thus staying robust while maximizing the expected future reward. Based on this setup, we propose a practical deep reinforcement learning algorithm, Adversarial Robust Policy Optimization (ARPO), to find a robust policy that generalizes to unseen environments. We evaluate our approach on Procgen and Distracting Control Suite for generalization and sample efficiency. Empirically, ARPO shows improved performance compared to a few baseline algorithms, including data augmen

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrahman2023adversarial

Related papers

• Robust And Diverse Multi-agent Learning Via Rational Policy Gradient (2025)0.00
• Attacking And Defending Deep Reinforcement Learning Policies (2022)0.00
• Robust Adversarial Policy Optimization Under Dynamics Uncertainty (2026)0.00
• ANO: A Principled Approach To Robust Policy Optimization (2026)0.00
• Generalization Of Reinforcement Learning With Policy-aware Adversarial Data Augmentation (2021)0.00
• Toward Evaluating Robustness Of Reinforcement Learning With Adversarial Policy (2023)4.52
• Adversarial Policies: Attacking Deep Reinforcement Learning (2019)0.00
• Robust Deep Reinforcement Learning With Adaptive Adversarial Perturbations In Action Space (2024)6.20