"Q-Advantage Integrated Human-Guided Reinforcement Learning for Safe End-to-End Autonomous Driving"

"This dataset contains the full implementation of the proposed Q-Advantage Integrated Human-Guided Reinforcement Learning (QIHG-RL) framework. The package includes PyTorch-based training scripts, model architectures, the Q-advantage integration module, prioritized replay buffer, and evaluation tools used in the experiments reported in the manuscript. The code enables full reproducibility of the experiments across the three safety-critical autonomous driving tasks."