{"ID":2883863,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.08170","arxiv_id":"2508.08170","title":"ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction","abstract":"Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial simulation-to-reality (sim2real) gap. To bridge this gap, some approaches utilize scene reconstruction techniques to create photorealistic environments as a simulator. While this improves realistic sensor simulation, these methods are inherently constrained by the distribution of the training data, making it difficult to render high-quality sensor data for novel trajectories or corner case scenarios. Therefore, we propose ReconDreamer-RL, a framework designed to integrate video diffusion priors into scene reconstruction to aid reinforcement learning, thereby enhancing end-to-end autonomous driving training. Specifically, in ReconDreamer-RL, we introduce ReconSimulator, which combines the video diffusion prior for appearance modeling and incorporates a kinematic model for physical modeling, thereby reconstructing driving scenarios from real-world data. This narrows the sim2real gap for closed-loop evaluation and reinforcement learning. To cover more corner-case scenarios, we introduce the Dynamic Adversary Agent (DAA), which adjusts the trajectories of surrounding vehicles relative to the ego vehicle, autonomously generating corner-case traffic scenarios (e.g., cut-in). Finally, the Cousin Trajectory Generator (CTG) is proposed to address the issue of training data distribution, which is often biased toward simple straight-line movements. Experiments show that ReconDreamer-RL improves end-to-end autonomous driving training, outperforming imitation learning methods with a 5x reduction in the Collision Ratio.","short_abstract":"Reinforcement learning for training end-to-end autonomous driving models in closed-loop simulations is gaining growing attention. However, most simulation environments differ significantly from real-world conditions, creating a substantial simulation-to-reality (sim2real) gap. To bridge this gap, some approaches utiliz...","url_abs":"https://arxiv.org/abs/2508.08170","url_pdf":"https://arxiv.org/pdf/2508.08170v2","authors":"[\"Chaojun Ni\",\"Guosheng Zhao\",\"Xiaofeng Wang\",\"Zheng Zhu\",\"Wenkang Qin\",\"Xinze Chen\",\"Guanghong Jia\",\"Guan Huang\",\"Wenjun Mei\"]","published":"2025-08-11T16:45:55Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Reinforcement Learning\",\"Diffusion Model\"]","has_code":false}