# ReconDreamer-RL: Enhancing Reinforcement Learning via Diffusion-based Scene Reconstruction

arXiv: https://arxiv.org/abs/2508.08170 · HTML: https://mlsanity.com/paper/2508.08170/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 27 of its 47 references that are in the map.
- First posted on arXiv 11 Aug 2025.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)
- Deep reinforcement learning methods / [RL for autonomous driving and traffic](https://mlsanity.com/deeprl/rl-for-autonomous-driving-and-traffic/)

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Scalability in Perception for Autonomous Driving: Waymo Open Dataset](https://mlsanity.com/paper/1912.04838/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [VAD: Vectorized Scene Representation for Efficient Autonomous Driving](https://mlsanity.com/paper/2303.12077/) (2023)
- [Exploring the Limitations of Behavior Cloning for Autonomous Driving](https://mlsanity.com/paper/1904.08980/) (2019)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [UniSim: A Neural Closed-Loop Sensor Simulator](https://mlsanity.com/paper/2308.01898/) (2023)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [Bridging Offline Reinforcement Learning and Imitation Learning: A Tale of Pessimism](https://mlsanity.com/paper/2103.12021/) (2021)
- [DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving](https://mlsanity.com/paper/2309.09777/) (2023)
- [SparseDrive: End-to-End Autonomous Driving via Sparse Scene Representation](https://mlsanity.com/paper/2405.19620/) (2024)
- [EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision](https://mlsanity.com/paper/2311.02077/) (2023)
- [PandaSet: Advanced Sensor Suite Dataset for Autonomous Driving](https://mlsanity.com/paper/2112.12610/) (2021)
- [MARS: An Instance-aware, Modular and Realistic Simulator for Autonomous Driving](https://mlsanity.com/paper/2307.15058/) (2023)
- [DriveDreamer4D: World Models Are Effective Data Machines for 4D Driving Scene Representation](https://mlsanity.com/paper/2410.13571/) (2024)
- [AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning](https://mlsanity.com/paper/2503.07608/) (2025)
- [ReconDreamer: Crafting World Models for Driving Scene Reconstruction via Online Restoration](https://mlsanity.com/paper/2411.19548/) (2024)
- [PLUTO: Pushing the Limit of Imitation Learning-based Planning for Autonomous Driving](https://mlsanity.com/paper/2404.14327/) (2024)
- [Keypoint Action Tokens Enable In-Context Imitation Learning in Robotics](https://mlsanity.com/paper/2403.19578/) (2024)
- [DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection](https://mlsanity.com/paper/2303.08730/) (2023)
- [Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning](https://mlsanity.com/paper/2410.05582/) (2024)
- [ReconDreamer++: Harmonizing Generative and Reconstructive Models for Driving Scene Representation](https://mlsanity.com/paper/2503.18438/) (2025)
- [EmbodieDreamer: Advancing Real2Sim2Real Transfer for Policy Training via Embodied World Modeling](https://mlsanity.com/paper/2507.05198/) (2025)
- [GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow](https://mlsanity.com/paper/2401.15803/) (2024)

## Built on by (most cited first, 27 of 27)

- [GigaWorld-Policy: An Efficient Action-Centered World--Action Model](https://mlsanity.com/paper/2603.17240/) (2026)
- [Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views](https://mlsanity.com/paper/2510.18632/) (2025)
- [GigaWorld-0: World Models as Data Engine to Empower Embodied AI](https://mlsanity.com/paper/2511.19861/) (2025)
- [DriveLaW:Unifying Planning and Video Generation in a Latent Driving World](https://mlsanity.com/paper/2512.23421/) (2025)
- [GigaBrain-0: A World Model-Powered Vision-Language-Action Model](https://mlsanity.com/paper/2510.19430/) (2025)
- [ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval](https://mlsanity.com/paper/2604.17898/) (2026)
- [SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead](https://mlsanity.com/paper/2512.00903/) (2025)
- [INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval](https://mlsanity.com/paper/2604.18051/) (2026)
- [GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning](https://mlsanity.com/paper/2602.12099/) (2026)
- [HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval](https://mlsanity.com/paper/2604.18037/) (2026)
- [OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention](https://mlsanity.com/paper/2602.05847/) (2026)
- [GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluation](https://mlsanity.com/paper/2607.02642/) (2026)
- [GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearch](https://mlsanity.com/paper/2607.13960/) (2026)
- [UniDriveDreamer: A Single-Stage Multimodal World Model for Autonomous Driving](https://mlsanity.com/paper/2602.02002/) (2026)
- [RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework](https://mlsanity.com/paper/2604.15308/) (2026)
- [Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends](https://mlsanity.com/paper/2606.01164/) (2026)
- [World Engine: Towards the Era of Post-Training for Autonomous Driving](https://mlsanity.com/paper/2606.19836/) (2026)
- [CATCH: A Modular Cross-domain Adaptive Template with Hook](https://mlsanity.com/paper/2510.26582/) (2025)
- [VAG: Dual-Stream Video-Action Generation for Embodied Data Synthesis](https://mlsanity.com/paper/2604.09330/) (2026)
- [RLGF: Reinforcement Learning with Geometric Feedback for Autonomous Driving Video Generation](https://mlsanity.com/paper/2509.16500/) (2025)
- [Scaling Self-Play for End-to-End Driving](https://mlsanity.com/paper/2606.19641/) (2026)
- [DriveZero: End-to-End Driving Beyond Human Demonstrations](https://mlsanity.com/paper/2609.06055/) (2026)
- [CRAFT: Counterfactual-to-Interactive Reinforcement Fine-Tuning for Driving Policies](https://mlsanity.com/paper/2605.04470/) (2026)
- [ReWorld: Representation Learning for World Action Models](https://mlsanity.com/paper/2606.27504/) (2026)
- [GSDrive: Reinforcing Driving Policies by Multi-mode Future Trajectory Probing with 3D Gaussian Splatting Environment](https://mlsanity.com/paper/2604.28111/) (2026)
- [From Generation to Simulation: How Far Are World Models from Being True Simulators?](https://mlsanity.com/paper/2608.23070/) (2026)
- [DreamStream: Towards Policy-Oriented Generative Simulation for End-to-End Driving](https://mlsanity.com/paper/2609.26792/) (2026)

## Abstract (arXiv)

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.