USER: A Unified and Extensible System for Real-World Online Policy Learning in Embodied AI
cs.RO
Submitted: 2026-02-08
Updated: 2026-10-09
Code: https://github.com/RLinf/RLinf
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- Reverb: A Framework For Experience Replay
- Challenges of Real-World Reinforcement Learning
- Acme: A Research Framework for Distributed Reinforcement Learning
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning
- SOP: A Scalable Online Post-Training System for Vision-Language-Action Models
- RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation
- SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
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
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies