tags:
- Embodied-AI
- Robotics
- Offline-to-Online-RL
- Value-Function
- VLA-Model
- Robot-Foundation-Model
- Vision-Language-Action
- Robot-Learning
- Imitation-Learning
Robo-ValueRL
[Project Page] [GitHub] [Paper]
This repository contains the models and data for Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning.
Robo-ValueRL studies how reliable value estimation can guide robotic policy learning from heterogeneous offline demonstrations and online rollout trajectories. The framework learns a history-conditioned value estimator, converts value differences into action-quality conditions for offline policy pretraining, and uses value-guided rollout filtering for stable online residual adaptation.
🤖 Model Description
Robo-ValueRL is an offline-to-online robotic reinforcement learning framework centered on reliable value estimation. Instead of only reporting final task success, Robo-ValueRL explicitly diagnoses whether learned values capture global task progress and local action-level preference, then propagates these value signals into downstream policy learning.
The released model suite includes:
History-Conditioned Value Estimator
Predicts normalized task progress from multi-view robot observations, language instructions, and visual history. The temporal context helps reduce ambiguity caused by occlusions, repeated motions, and visually similar task stages.Quality-Conditioned VLA Policy
Uses value differences to derive action-quality conditions. These conditions guide a Vision-Language-Action policy during offline pretraining, allowing the policy to prioritize useful behaviors from mixed-quality demonstrations.Online Residual Adaptation Module
Learns lightweight corrections from value-filtered online rollouts while keeping the pretrained base policy frozen. This enables targeted failure recovery and self-correction without overwriting the offline prior.
📦 Data Description
The Robo-ValueRL dataset contains heterogeneous real-robot experience collected on two long-horizon manipulation tasks:
- Chip Insertion: millimeter-level precision manipulation requiring PCB grasping, pose adjustment, chip grasping, and insertion.
- Block Disassembly: generalizable object disassembly requiring robust grasping, separation, and classification behaviors.
The dataset includes:
- 240 hours of offline demonstrations
- 3,000+ online rollout trajectories
- Multi-view robot observations
- Language task instructions
- Robot states and action chunks
- Mixed-quality trajectories, including successful demonstrations, corrections, suboptimal behaviors, and failure cases
- Value-derived action-quality labels / conditions for policy learning
- Online rollout segments for residual adaptation
🧱 Model Hierarchy
Value Estimation
- Learns history-conditioned value functions from heterogeneous robot data.
- Evaluates value reliability with global-progress and local-preference metrics.
Offline Policy Pretraining
- Converts value differences into action-quality conditions.
- Trains a quality-conditioned VLA policy on mixed-quality demonstrations.
Online Policy Improvement
- Uses reliable value estimates to filter online rollout data.
- Trains a lightweight residual adapter for targeted real-world improvement.
✨ Key Features
- Reliable Value Estimation: Uses visual history to produce smoother progress estimates and sharper error responses.
- Value-Guided Data Utilization: Prioritizes useful demonstrations and rollout segments from heterogeneous robot experience.
- Quality-Conditioned Policy Learning: Conditions the VLA policy on value-derived action quality.
- Stable Offline-to-Online Improvement: Improves real-world performance through residual adaptation while preserving the pretrained base policy.
- Real-Robot Evaluation: Evaluated on precision chip insertion and generalizable block disassembly.
📊 Highlights
- 86% final success on chip insertion
- 84% final success on block disassembly
- +26% offline gain on chip insertion
- +34% offline gain on block disassembly
- 240h offline demonstrations
- 3,000+ online rollout trajectories
🛠 Usage
The released assets are organized for reproducing Robo-ValueRL's model and data pipeline.
Typical usage includes:
- Load the offline demonstration dataset.
- Train or evaluate the history-conditioned value estimator.
- Derive action-quality conditions from value differences.
- Train the quality-conditioned VLA policy.
- Use online rollout data to train the residual adaptation module.
Please refer to the GitHub repository for setup instructions, inference scripts, training code, and data-processing utilities.
📁 Repository Contents
This release may include:
- Value estimator checkpoints
- Quality-conditioned VLA policy checkpoints
- Online residual adapter checkpoints
- Offline demonstration data
- Online rollout trajectories
- Value labels and action-quality conditions
- Evaluation scripts
- Visualization and analysis tools
📝 Citation
Citation will be updated after the arXiv release.
# Coming soon
📜 License
Please refer to the license file in the GitHub repository.
📬 Contact
For questions, please open an issue on our GitHub repository.