# Self-Improving Safety Performance of Reinforcement Learning Based Driving with Black-Box Verification Algorithms

arXiv: https://arxiv.org/abs/2210.16575 · HTML: https://mlsanity.com/paper/2210.16575/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving.
- Builds on 13 of its 23 references that are in the map.
- First posted on arXiv 29 Oct 2022.

## Placed in

- End-to-end autonomous driving / [Reinforcement learning for driving](https://mlsanity.com/driving/reinforcement-learning-for-driving/)

## Builds on (most cited first, 13 of 13)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Scalable End-to-End Autonomous Vehicle Testing via Rare-event Simulation](https://mlsanity.com/paper/1811.00145/) (2018)
- [Adaptive Stress Testing for Autonomous Vehicles](https://mlsanity.com/paper/1902.01909/) (2019)
- [RLlib: Abstractions for Distributed Reinforcement Learning](https://mlsanity.com/paper/1712.09381/) (2017)
- [Neural Bridge Sampling for Evaluating Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2008.10581/) (2020)
- [Training Adversarial Agents to Exploit Weaknesses in Deep Control Policies](https://mlsanity.com/paper/2002.12078/) (2020)
- [Efficient Black-box Assessment of Autonomous Vehicle Safety](https://mlsanity.com/paper/1912.03618/) (2019)
- [Automated Lane Change Decision Making using Deep Reinforcement Learning in Dynamic and Uncertain Highway Environment](https://mlsanity.com/paper/1909.11538/) (2019)
- [Prediction-Based Reachability for Collision Avoidance in Autonomous Driving](https://mlsanity.com/paper/2011.12406/) (2020)
- [Interpretable Safety Validation for Autonomous Vehicles](https://mlsanity.com/paper/2004.06805/) (2020)
- [Sample Efficient Interactive End-to-End Deep Learning for Self-Driving Cars with Selective Multi-Class Safe Dataset Aggregation](https://mlsanity.com/paper/2007.14671/) (2020)
- [SAINT-ACC: Safety-Aware Intelligent Adaptive Cruise Control for Autonomous Vehicles Using Deep Reinforcement Learning](https://mlsanity.com/paper/2104.06506/) (2021)
- [I Know You Can't See Me: Dynamic Occlusion-Aware Safety Validation of Strategic Planners for Autonomous Vehicles Using Hypergames](https://mlsanity.com/paper/2109.09807/) (2021)

## Built on by (most cited first, 4 of 4)

- [AEGIS: Human Attention-based Explainable Guidance for Intelligent Vehicle Systems](https://mlsanity.com/paper/2504.05950/) (2025)
- [Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents](https://mlsanity.com/paper/2602.05810/) (2026)
- [Navigating the Edge with the State-of-the-Art Insights into Corner Case Identification and Generation for Enhanced Autonomous Vehicle Safety](https://mlsanity.com/paper/2503.00077/) (2025)
- [CORTEX-AVD: A Framework for CORner Case Testing and EXploration in Autonomous Vehicle Development](https://mlsanity.com/paper/2504.03989/) (2025)

## Abstract (arXiv)

In this work, we propose a self-improving artificial intelligence system to enhance the safety performance of reinforcement learning (RL)-based autonomous driving (AD) agents using black-box verification methods. RL algorithms have become popular in AD applications in recent years. However, the performance of existing RL algorithms heavily depends on the diversity of training scenarios. A lack of safety-critical scenarios during the training phase could result in poor generalization performance in real-world driving applications. We propose a novel framework in which the weaknesses of the training set are explored through black-box verification methods. After discovering AD failure scenarios, the RL agent's training is re-initiated via transfer learning to improve the performance of previously unsafe scenarios. Simulation results demonstrate that our approach efficiently discovers safety failures of action decisions in RL-based adaptive cruise control (ACC) applications and significantly reduces the number of vehicle collisions through iterative applications of our method. The source code is publicly available at https://github.com/data-and-decision-lab/self-improving-RL.