Papers › Self-Improving Safety Performance of Reinforcement Learning Based Driving with...

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

29 Oct 2022arXiv:2210.16575archive 2025-07-28

Resul Dagdanov, Halil Durmus, Nazim Kemal Ure

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.

Paper PDF Code

Code

data-and-decision-lab/self-improving-RL officialmentioned in papermentioned on GitHubpytorch report

resuldagdanov/self-improving-RL mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Autonomous Driving Diversity Reinforcement Learning (RL)Safe Reinforcement Learning Self-Learning Transfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Discriminative Adversarial Search Entropy Regularization Monte-Carlo Tree Search PPO Selective Search Self-Adversarial Negative Sampling Self-adaptive Training

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections