# Improved Robustness and Safety for Autonomous Vehicle Control with Adversarial Reinforcement Learning

arXiv: https://arxiv.org/abs/1903.03642 · HTML: https://mlsanity.com/paper/1903.03642/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Mar 2019.

## Built on by (most cited first, 23 of 23)

- [CAT: Closed-loop Adversarial Training for Safe End-to-End Driving](https://mlsanity.com/paper/2310.12432/) (2023)
- [Large-scale Robustness Analysis of Video Action Recognition Models](https://mlsanity.com/paper/2207.01398/) (2022)
- [Robustness Analysis of Video-Language Models Against Visual and Language Perturbations](https://mlsanity.com/paper/2207.02159/) (2022)
- [Reevaluating Policy Gradient Methods for Imperfect-Information Games](https://mlsanity.com/paper/2502.08938/) (2025)
- [A Survey of Deep Reinforcement Learning Algorithms for Motion Planning and Control of Autonomous Vehicles](https://mlsanity.com/paper/2105.14218/) (2021)
- [Robust Imitation Learning from Corrupted Demonstrations](https://mlsanity.com/paper/2201.12594/) (2022)
- [Performance Analysis of Out-of-Distribution Detection on Trained Neural Networks](https://mlsanity.com/paper/2204.12378/) (2022)
- [Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments](https://mlsanity.com/paper/2207.09597/) (2022)
- [Traffic-Aware Autonomous Driving with Differentiable Traffic Simulation](https://mlsanity.com/paper/2210.03772/) (2022)
- [Improving Robustness of Deep Reinforcement Learning Agents: Environment Attack based on the Critic Network](https://mlsanity.com/paper/2104.03154/) (2021)
- [ARC: Adversarially Robust Control Policies for Autonomous Vehicles](https://mlsanity.com/paper/2107.04487/) (2021)
- [ADV-0: Closed-Loop Min-Max Adversarial Training for Long-Tail Robustness in Autonomous Driving](https://mlsanity.com/paper/2603.15221/) (2026)
- [Off Environment Evaluation Using Convex Risk Minimization](https://mlsanity.com/paper/2112.11532/) (2021)
- [Evaluating Robustness over High Level Driving Instruction for Autonomous Driving](https://mlsanity.com/paper/2105.10014/) (2021)
- [Understanding the Impact of Edge Cases from Occluded Pedestrians for ML Systems](https://mlsanity.com/paper/2204.12402/) (2022)
- [Robust AI Driving Strategy for Autonomous Vehicles](https://mlsanity.com/paper/2207.07829/) (2022)
- [Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning](https://mlsanity.com/paper/2212.08961/) (2022)
- [Deep incremental learning models for financial temporal tabular datasets with distribution shifts](https://mlsanity.com/paper/2303.07925/) (2023)
- [Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning](https://mlsanity.com/paper/2311.15089/) (2023)
- [Robust Driving Control for Autonomous Vehicles: An Intelligent General-sum Constrained Adversarial Reinforcement Learning Approach](https://mlsanity.com/paper/2510.09041/) (2025)
- [Measuring Interventional Robustness in Reinforcement Learning](https://mlsanity.com/paper/2209.09058/) (2022)
- [Smoothing Policy Iteration for Zero-sum Markov Games](https://mlsanity.com/paper/2212.01623/) (2022)
- [Reward-Preserving Attacks For Robust Reinforcement Learning](https://mlsanity.com/paper/2601.07118/) (2026)

## Abstract (arXiv)

To improve efficiency and reduce failures in autonomous vehicles, research has focused on developing robust and safe learning methods that take into account disturbances in the environment. Existing literature in robust reinforcement learning poses the learning problem as a two player game between the autonomous system and disturbances. This paper examines two different algorithms to solve the game, Robust Adversarial Reinforcement Learning and Neural Fictitious Self Play, and compares performance on an autonomous driving scenario. We extend the game formulation to a semi-competitive setting and demonstrate that the resulting adversary better captures meaningful disturbances that lead to better overall performance. The resulting robust policy exhibits improved driving efficiency while effectively reducing collision rates compared to baseline control policies produced by traditional reinforcement learning methods.