Stable and Efficient Real-World Online VLA Post-Training via Asynchronous Replay-Anchored Policy Improvement
cs.RO
Submitted: 2026-09-19
Updated: 2026-09-19
Project page: https://flyfaerss.github.io/RAPolicy
Terminology
Sources
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- RL Token: Bootstrapping Online RL with Vision-Language-Action Models
- ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
- Massively Parallel Methods for Deep Reinforcement Learning
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Distributed Prioritized Experience Replay
- Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
- Conservative Q-Learning for Offline Reinforcement Learning
- QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
- SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
- Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
- Policy Agnostic RL: Offline RL and Online RL Fine-Tuning of Any Class and Backbone
- EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
- AWAC: Accelerating Online Reinforcement Learning with Offline Datasets
- HG-DAgger: Interactive Imitation Learning with Human Experts
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