DexPIE: Stable Dexterous Policy Improvement from Real-World Experience
cs.RO, cs.CV
Submitted: 2026-06-08
Updated: 2026-10-06
Code: https://github.com/MINT-SJTU/Evo-RL
Project page: https://siiuuuuuu.github.io/DexPIE
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency Policy
- GR-RL: Going Dexterous and Precise for Long-Horizon Robotic Manipulation
- ALOE: Action-Level Off-Policy Evaluation for Vision-Language-Action Model Post-Training
- RLDG: Robotic Generalist Policy Distillation via Reinforcement Learning
- SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
- ReWiND: Language-Guided Rewards Teach Robot Policies without New Demonstrations
- ARM: Advantage Reward Modeling for Long-Horizon Manipulation
- $\chi_{0}$: Resource-Aware Robust Manipulation via Taming Distributional Inconsistencies
- Training-Time Action Conditioning for Efficient Real-Time Chunking
- VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
- ACE: A Cross-Platform Visual-Exoskeletons System for Low-Cost Dexterous Teleoperation
- DexCap: Scalable and Portable Mocap Data Collection System for Dexterous Manipulation
- AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
- RaC: Robot Learning for Long-Horizon Tasks by Scaling Recovery and Correction
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