# OPTED: On-Policy Fine-Tuning for End-to-End Driving using a Render-Free Teacher

arXiv: https://arxiv.org/abs/2609.20756 · HTML: https://mlsanity.com/paper/2609.20756/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving.
- Builds on 30 of its 38 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## Placed in

- End-to-end autonomous driving / [Imitation-learning end-to-end planners](https://mlsanity.com/driving/imitation-learning-end-to-end-planners/)

## Builds on (most cited first, 30 of 30)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [CARLA: An Open Urban Driving Simulator](https://mlsanity.com/paper/1711.03938/) (2017)
- [Large Scale Interactive Motion Forecasting for Autonomous Driving : The Waymo Open Motion Dataset](https://mlsanity.com/paper/2104.10133/) (2021)
- [NuPlan: A closed-loop ML-based planning benchmark for autonomous vehicles](https://mlsanity.com/paper/2106.11810/) (2021)
- [ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worst](https://mlsanity.com/paper/1812.03079/) (2018)
- [Learning by Cheating](https://mlsanity.com/paper/1912.12294/) (2019)
- [Trajectory-guided Control Prediction for End-to-end Autonomous Driving: A Simple yet Strong Baseline](https://mlsanity.com/paper/2206.08129/) (2022)
- [End-to-End Urban Driving by Imitating a Reinforcement Learning Coach](https://mlsanity.com/paper/2108.08265/) (2021)
- [GenAD: Generalized Predictive Model for Autonomous Driving](https://mlsanity.com/paper/2403.09630/) (2024)
- [Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail](https://mlsanity.com/paper/2511.00088/) (2025)
- [DriveAdapter: Breaking the Coupling Barrier of Perception and Planning in End-to-End Autonomous Driving](https://mlsanity.com/paper/2308.00398/) (2023)
- [Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction](https://mlsanity.com/paper/1703.01030/) (2017)
- [RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning](https://mlsanity.com/paper/2502.13144/) (2025)
- [Robust Autonomy Emerges from Self-Play](https://mlsanity.com/paper/2502.03349/) (2025)
- [GPUDrive: Data-driven, multi-agent driving simulation at 1 million FPS](https://mlsanity.com/paper/2408.01584/) (2024)
- [Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models](https://mlsanity.com/paper/2412.05334/) (2024)
- [VaViM and VaVAM: Autonomous Driving through Video Generative Modeling](https://mlsanity.com/paper/2502.15672/) (2025)
- [CaRL: Learning Scalable Planning Policies with Simple Rewards](https://mlsanity.com/paper/2504.17838/) (2025)
- [LEAD: Minimizing Learner-Expert Asymmetry in End-to-End Driving](https://mlsanity.com/paper/2512.20563/) (2025)
- [Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling](https://mlsanity.com/paper/2505.17659/) (2025)
- [Advancing Multi-agent Traffic Simulation via R1-Style Reinforcement Fine-Tuning](https://mlsanity.com/paper/2509.23993/) (2025)
- [PlannerRFT: Reinforcing Diffusion Planners through Closed-Loop and Sample-Efficient Fine-Tuning](https://mlsanity.com/paper/2601.12901/) (2026)
- [Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving](https://mlsanity.com/paper/2609.00111/) (2026)
- [RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework](https://mlsanity.com/paper/2604.15308/) (2026)
- [World Engine: Towards the Era of Post-Training for Autonomous Driving](https://mlsanity.com/paper/2606.19836/) (2026)
- [RoaD: Rollouts as Demonstrations for Closed-Loop Supervised Fine-Tuning of Autonomous Driving Policies](https://mlsanity.com/paper/2512.01993/) (2025)
- [Scaling Self-Play for End-to-End Driving](https://mlsanity.com/paper/2606.19641/) (2026)
- [TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations](https://mlsanity.com/paper/2606.17386/) (2026)
- [Pictura: Perspective-View Self-Play at Scale for Driving](https://mlsanity.com/paper/2607.26005/) (2026)

## Built on by (most cited first, 1 of 1)

- [Guiding End-to-End Driving Models with Endpoint-Constrained Trajectory Optimization](https://mlsanity.com/paper/2609.31383/) (2026)

## Abstract (arXiv)

As scaling pre-training data alone yields diminishing returns, post-training is becoming increasingly important across physical AI domains such as autonomous driving. End-to-end driving policies are pre-trained in open loop with behavior cloning on human demonstrations. However, compounding errors during closed-loop deployment can take the vehicle outside the training data distribution, increasing the risk of safety-critical incidents. Closed-loop post-training can mitigate this risk but requires costly simulation for sensor-based policies. We propose OPTED (on-policy fine-tuning for end-to-end driving) which decouples reinforcement learning from the post-training of the end-to-end policy: a privileged teacher is trained using RL on vectorized inputs (HD-map and bounding boxes). This teacher then provides supervision to the pre-trained student during closed-loop post-training. We apply OPTED to two camera-based models, TransFuser and VaVAM, and fine-tune them in AlpaSim, using neural reconstructions (3DGS) of real driving logs. Driving scores increase by factors of 1.6× and 9.5×, respectively. In controlled experiments OPTED matches closed-loop performance with approximately three orders of magnitude fewer simulator interactions than direct RL post-training, while staying closer to the human prior. Project page: https://01dami23.github.io/opted/