# DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

arXiv: https://arxiv.org/abs/2603.24587 · HTML: https://mlsanity.com/paper/2603.24587/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in World models for autonomous driving, one of 11 directions in World models.
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 25 Mar 2026.

## Placed in

- World models / [World models for autonomous driving](https://mlsanity.com/wm/world-models-for-autonomous-driving/)
- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- End-to-end autonomous driving / [Generative simulation for driving](https://mlsanity.com/driving/generative-simulation-for-driving/)
- 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, 24 of 24)

- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [One Step Diffusion via Shortcut Models](https://mlsanity.com/paper/2410.12557/) (2024)
- [NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking](https://mlsanity.com/paper/2406.15349/) (2024)
- [VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning](https://mlsanity.com/paper/2402.13243/) (2024)
- [AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning](https://mlsanity.com/paper/2506.13757/) (2025)
- [MagicDrive: Street View Generation with Diverse 3D Geometry Control](https://mlsanity.com/paper/2310.02601/) (2023)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [Stochastic Variational Video Prediction](https://mlsanity.com/paper/1710.11252/) (2017)
- [DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Driving](https://mlsanity.com/paper/2510.12796/) (2025)
- [World4Drive: End-to-End Autonomous Driving via Intention-aware Physical Latent World Model](https://mlsanity.com/paper/2507.00603/) (2025)
- [DRAMA: An Efficient End-to-end Motion Planner for Autonomous Driving with Mamba](https://mlsanity.com/paper/2408.03601/) (2024)
- [RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning](https://mlsanity.com/paper/2502.13144/) (2025)
- [WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL](https://mlsanity.com/paper/2602.13977/) (2026)
- [ReSim: Reliable World Simulation for Autonomous Driving](https://mlsanity.com/paper/2506.09981/) (2025)
- [World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation](https://mlsanity.com/paper/2509.19080/) (2025)
- [OmniNWM: Omniscient Driving Navigation World Models](https://mlsanity.com/paper/2510.18313/) (2025)
- [WorldRFT: Latent World Model Planning with Reinforcement Fine-Tuning for Autonomous Driving](https://mlsanity.com/paper/2512.19133/) (2025)
- [AD-R1: Closed-Loop Reinforcement Learning for End-to-End Autonomous Driving with Impartial World Models](https://mlsanity.com/paper/2511.20325/) (2025)
- [Novel Approaches for ML-Assisted Particle Track Reconstruction and Hit Clustering](https://mlsanity.com/paper/2405.17325/) (2024)

## Built on by (most cited first, 15 of 15)

- [RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework](https://mlsanity.com/paper/2604.15308/) (2026)
- [WA-JEPA: Rethinking the Video JEPA Paradigm for World-Action Modeling in Autonomous Driving](https://mlsanity.com/paper/2608.20974/) (2026)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning](https://mlsanity.com/paper/2606.05645/) (2026)
- [RISE: Adaptive Imagination for World Action Models](https://mlsanity.com/paper/2608.20430/) (2026)
- [World Models as Group Actions](https://mlsanity.com/paper/2605.24578/) (2026)
- [ForgeDrive: Bidirectional Cross-Conditioning for Unified Visual-Action Generation in Autonomous Driving](https://mlsanity.com/paper/2606.31226/) (2026)
- [Post-Training in End-to-End Autonomous Driving](https://mlsanity.com/paper/2607.08072/) (2026)
- [HyWorldVLA: A Vision-Language-Action Model with Hybrid World Modeling for Autonomous Driving](https://mlsanity.com/paper/2607.20988/) (2026)
- [SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action Models](https://mlsanity.com/paper/2610.13781/) (2026)
- [Ego-Dynamics-Augmented World Model for Autonomous Driving with Zero-Shot Cross-Embodiment Adaptation](https://mlsanity.com/paper/2607.13410/) (2026)
- [DriveVLA-M0: Failure-Aware Memory Augmentation for Autonomous Driving](https://mlsanity.com/paper/2608.10413/) (2026)
- [ZYT-World: A Real-Time Controllable World Model for Closed-Loop Autonomous-Driving Simulation](https://mlsanity.com/paper/2609.21712/) (2026)
- [ReDrive: Shaping Representations with World Modeling for End-to-End Driving](https://mlsanity.com/paper/2609.33854/) (2026)
- [MORE: Learning Motion-Oriented Registers for Driving World Models and Planning](https://mlsanity.com/paper/2610.14871/) (2026)

## Abstract (arXiv)

We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual interpretability. Training RL policies on real-world driving data incurs prohibitive costs and safety risks. While existing pixel-level diffusion world models enable safe imagination-based training, they suffer from multi-step diffusion inference latency (2s/frame) that prevents high-frequency RL interaction. Our approach leverages denoised latent features from video generation models through three key mechanisms: (1) shortcut forcing that reduces sampling complexity via recursive multi-resolution step compression, (2) an autoregressive dense reward model operating directly on latent representations for fine-grained credit assignment, and (3) Gaussian vocabulary sampling for GRPO that constrains exploration to physically plausible trajectories. DreamerAD achieves 87.7 EPDMS on NavSim v2, establishing state-of-the-art performance and demonstrating that latent-space RL is effective for autonomous driving.