Learning While Deploying: Fleet-Scale Reinforcement Learning for Generalist Robot Policies
cs.RO
Submitted: 2026-05-01
Updated: 2026-09-16
Comments: Project page: https://learning-while-deploying.github.io/
Project page: https://learning-while-deploying.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RT-1: Robotics Transformer for Real-World Control at Scale
- Octo: An Open-Source Generalist Robot Policy
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learning
- GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
- ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
- Interactive Post-Training for Vision-Language-Action Models
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- Flow-GRPO: Training Flow Matching Models via Online RL
- ReinFlow: Fine-tuning Flow Matching Policy with Online Reinforcement Learning
- Offline Reinforcement Learning with Implicit Q-Learning
- Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
- Q-learning with Adjoint Matching
- GRAPE: Generalizing Robot Policy via Preference Alignment
- RLinf-VLA: A Unified and Efficient Framework for Reinforcement Learning of Vision-Language-Action Models
- What Can RL Bring to VLA Generalization? An Empirical Study
- RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
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