# RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies

## TL;DR

This paper introduces RL-based techniques to quantitatively benchmark the adversarial resilience and robustness of deep reinforcement learning policies, distinguishing vulnerabilities from representation learning and policy sensitivity.

## Contribution

It presents novel RL-based methods for disentangling vulnerabilities and benchmarking DRL policies against adversarial state perturbations.

## Key findings

- Effective disentanglement of vulnerabilities from representation learning.
- Successful benchmarking of DQN, A2C, and PPO2 policies.
- Demonstrated resilience and robustness measures in Cartpole environment.

## Abstract

This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities caused by representation learning of DRL agents from those that stem from the sensitivity of the DRL policies to distributional shifts in state transitions. Building on this approach, we propose two RL-based techniques for quantitative benchmarking of adversarial resilience and robustness in DRL policies against perturbations of state transitions. We demonstrate the feasibility of our proposals through experimental evaluation of resilience and robustness in DQN, A2C, and PPO2 policies trained in the Cartpole environment.