Learning to Act While Waiting: RL Finetuning of Generalist Robot Policies Under Inference Latency
cs.RO, cs.LG
Submitted: 2026-08-24
Updated: 2026-08-26
Comments: 25 pages, 12 figures, project website: https://async-rl-intermediate-information.github.io/
Code: https://github.com/Physical-Intelligence/openpi
Project page: https://async-rl-intermediate-information.github.io
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- RT-1: Robotics Transformer for Real-World Control at Scale
- RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches
- OpenVLA: An Open-Source Vision-Language-Action Model
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Gemini Robotics: Bringing AI into the Physical World
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer
- Steering Your Diffusion Policy with Latent Space Reinforcement Learning
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
- From Prior to Pro: Efficient Skill Mastery via Distribution Contractive RL Finetuning
- FlowDAgger: Human-in-the-Loop Adaptation of Generative Robot Policies in Latent Space
- Robot Self-Improvement via Human-Video Dynamics Models
- Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
- Training-Time Action Conditioning for Efficient Real-Time Chunking
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
- World Action Models are Zero-shot Policies
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
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