README.md

---
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](https://gewu-lab.github.io/robo-valuerl/)] [[GitHub](https://github.com/Open-X-Humanoid/Robo-ValueRL)] [[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:

1. **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.

2. **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.

3. **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

1. **Value Estimation**
   - Learns history-conditioned value functions from heterogeneous robot data.
   - Evaluates value reliability with global-progress and local-preference metrics.

2. **Offline Policy Pretraining**
   - Converts value differences into action-quality conditions.
   - Trains a quality-conditioned VLA policy on mixed-quality demonstrations.

3. **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:

1. Load the offline demonstration dataset.
2. Train or evaluate the history-conditioned value estimator.
3. Derive action-quality conditions from value differences.
4. Train the quality-conditioned VLA policy.
5. Use online rollout data to train the residual adaptation module.

Please refer to the [GitHub repository](https://github.com/Open-X-Humanoid/Robo-ValueRL) 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.

```bibtex
# Coming soon
📜 License
Please refer to the license file in the GitHub repository.
📬 Contact
For questions, please open an issue on our GitHub repository.