VLA-Precision: Asymmetric Co-Bootstrapping for Efficient Real-World Online RL of Vision-Language-Action Models
cs.RO, cs.AI, cs.HC, cs.LG
Submitted: 2026-09-03
Updated: 2026-09-18
Comments: 17 pages, 14 figures
Project page: https://vla-precision.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- Real-world Reinforcement Learning from Suboptimal Interventions
- Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models
- Interactive Post-Training for Vision-Language-Action Models
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
- SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving