# Robust Deep Reinforcement Learning Through Adversarial Attacks and Training : A Survey

arXiv: https://arxiv.org/abs/2403.00420 · HTML: https://mlsanity.com/paper/2403.00420/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Adversarial robustness and RL in finance, one of 15 directions in Deep reinforcement learning methods.
- First posted on arXiv 1 Mar 2024.

## Placed in

- Deep reinforcement learning methods / [Adversarial robustness and RL in finance](https://mlsanity.com/deeprl/adversarial-robustness-and-rl-in-finance/)

## Built on by (most cited first, 13 of 13)

- [State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning](https://mlsanity.com/paper/2503.20613/) (2025)
- [Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks](https://mlsanity.com/paper/2503.20844/) (2025)
- [Robust Deep Reinforcement Learning against Adversarial Behavior Manipulation](https://mlsanity.com/paper/2406.03862/) (2024)
- [Decentralized Consensus Inference-based Hierarchical Reinforcement Learning for Multi-Constrained UAV Pursuit-Evasion Game](https://mlsanity.com/paper/2506.18126/) (2025)
- [Lipschitz-Regularized Critics Lead to Policy Robustness Against Transition Dynamics Uncertainty](https://mlsanity.com/paper/2404.13879/) (2024)
- [Dynamic Obstacle Avoidance with Bounded Rationality Adversarial Reinforcement Learning](https://mlsanity.com/paper/2503.11467/) (2025)
- [Off-Policy Actor-Critic for Adversarial Observation Robustness: Virtual Alternative Training via Symmetric Policy Evaluation](https://mlsanity.com/paper/2506.16753/) (2025)
- [A Dynamical Systems Framework for Reinforcement Learning Safety and Robustness Verification](https://mlsanity.com/paper/2508.15588/) (2025)
- [Sparse Threats, Focused Defense: Criticality-Aware Robust Reinforcement Learning for Safe Autonomous Driving](https://mlsanity.com/paper/2601.01800/) (2026)
- [Reward-Preserving Attacks For Robust Reinforcement Learning](https://mlsanity.com/paper/2601.07118/) (2026)
- [Advantage-based Temporal Attack in Reinforcement Learning](https://mlsanity.com/paper/2602.19582/) (2026)
- [Taming the Adversary: A Cost-to-Disturbance Ratio Approach to Adversarial Reinforcement Learning](https://mlsanity.com/paper/2603.12110/) (2026)
- [Beyond Coefficients: Forecast-Necessity Testing for Interpretable Causal Discovery in Nonlinear Time-Series Models](https://mlsanity.com/paper/2604.18751/) (2026)

## Abstract (arXiv)

Deep Reinforcement Learning (DRL) is a subfield of machine learning for training autonomous agents that take sequential actions across complex environments. Despite its significant performance in well-known environments, it remains susceptible to minor condition variations, raising concerns about its reliability in real-world applications. To improve usability, DRL must demonstrate trustworthiness and robustness. A way to improve the robustness of DRL to unknown changes in the environmental conditions and possible perturbations is through Adversarial Training, by training the agent against well-suited adversarial attacks on the observations and the dynamics of the environment. Addressing this critical issue, our work presents an in-depth analysis of contemporary adversarial attack and training methodologies, systematically categorizing them and comparing their objectives and operational mechanisms.