Beyond Policy Patches: Distilling RL Specialists into Vision-Language-Action Policies
cs.RO
Submitted: 2026-11-02
Updated: 2026-11-02
Project page: https://repair-vla.github.io
Terminology
Sources
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
- Posterior Optimization with Clipped Objective for Bridging Efficiency and Stability in Generative Policy Learning
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation
- WoVR: World Models as Reliable Simulators for Post-Training VLA Policies with RL
- RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
- Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
- Q-VGM: Q-Guided Value-Gradient Matching for Offline-to-Online RL of Flow-Matching VLA Policies
- Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
- RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- Beyond Human Demonstrations: Diffusion-Based Reinforcement Learning to Generate Data for VLA Training
- Beyond Action Residuals: Real-World Robot Policy Steering via Bottleneck Latent Reinforcement Learning
- RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
- USER: A Unified and Extensible System for Online Real-World Policy Learning in Embodied AI
Related papers
- Rethinking Actions: Continuity-Aware Priors for World-Model Planning
- MOSAIC: Modular Obstacle and Spatial-Aware Framework for Manipulation In Cluttered Scenes
- SAGAS: Semantic-Aware Graph-Assisted Stitching for Offline Temporal Logic Planning
- DexSeed: Expanding Human Hand-Object Interactions into Robot Demonstrations for Dexterous Policy Learning
- LaST0.5: A Generalist World Action Model with Interaction-Centric Latent Reasoning
- CIALLO: Learning Shared Intent Representations for Cross-Embodiment Manipulation