---
license: mit
tags:
- RLinf
language:
- en
metrics:
- accuracy
base_model:
- Haozhan72/Openvla-oft-SFT-libero-spatial-traj1
pipeline_tag: reinforcement-learning
model-index:
- name: RLinf-OpenVLAOFT-GRPO-LIBERO-spatial
  results:
  - task:
      type: VLA             # Required. Example: automatic-speech-recognition
    dataset:
      type: libero_spatial          # Required. Example: common_voice. Use dataset id from https://hf.co/datasets
      name: libero_spatial         # Required. A pretty name for the dataset. Example: Common Voice (French)
    metrics:
      - type: accuracy        # Required. Example: wer. Use metric id from https://hf.co/metrics
        value: 98.99      # Required. Example: 20.90
---

<div align="center">
  <img src="logo.svg" alt="RLinf-logo" width="500"/>
</div>


<div align="center">
<!-- <a href="TODO"><img src="https://img.shields.io/badge/arXiv-Paper-red?logo=arxiv"></a> -->
<!-- <a href="TODO"><img src="https://img.shields.io/badge/HuggingFace-yellow?logo=huggingface&logoColor=white" alt="Hugging Face"></a> -->
<a href="https://github.com/RLinf/RLinf"><img src="https://img.shields.io/badge/Github-blue"></a>
<a href="https://rlinf.readthedocs.io/en/latest/"><img src="https://img.shields.io/badge/Documentation-Purple?color=8A2BE2&logo=readthedocs"></a>
<!-- <a href="TODO"><img src="https://devin.ai/assets/deepwiki-badge.png" alt="Ask DeepWiki.com" style="height:20px;"></a>
<a href="TODO"><img src="https://img.shields.io/badge/微信-green?logo=wechat&amp"></a> -->
</div>

<h1 align="center">RLinf: Reinforcement Learning Infrastructure for Agentic AI</h1>

[RLinf](https://github.com/RLinf/RLinf) is a flexible and scalable open-source infrastructure designed for post-training foundation models (LLMs, VLMs, VLAs) via reinforcement learning. The 'inf' in RLinf stands for Infrastructure, highlighting its role as a robust backbone for next-generation training. It also stands for Infinite, symbolizing the system’s support for open-ended learning, continuous generalization, and limitless possibilities in intelligence development.


<div align="center">
  <img src="overview.png" alt="RLinf-overview" width="600"/>
</div>

## Model Description
The RLinf-openvlaoft-libero series is trained on Haozhan72/Openvla-oft-SFT-libero-xxx-traj1 (including libero10, libero-object, libero-goal and libero-spatial), using the same base models and training datasets as verl. Training with RLinf yields SOTA performance.

We use a mask to focus on valid action tokens, and compute token-level loss based on the Group Relative Policy Optimization (GRPO) advantage function, in order to enhance the model’s performance on spatial reasoning, object generalization, instruction generalization, and long-horizon tasks.


## Evaluation and Results
We trained and evaluated four models using RLinf:

- RLinf-openvlaoft-libero-object Model (based on [Haozhan72/Openvla-oft-SFT-libero-object-traj1](https://huggingface.co/Haozhan72/Openvla-oft-SFT-libero-object-traj1))
  - Recommended sampling settings:  `temperature = 1.6`, `top_p = 1.0`

- RLinf-openvlaoft-libero-spatial Model (based on [Haozhan72/Openvla-oft-SFT-libero-spatial-traj1](https://huggingface.co/Haozhan72/Openvla-oft-SFT-libero-spatial-traj1))
  - Recommended sampling settings:  `temperature = 1.6`, `top_p = 1.0`

- RLinf-openvlaoft-libero-goal Model (based on [Haozhan72/Openvla-oft-SFT-libero-goal-traj1]((https://huggingface.co/Haozhan72/Openvla-oft-SFT-libero-goal-traj1)))
  - Recommended sampling settings:  `temperature = 1.6`, `top_p = 1.0`

- RLinf-openvlaoft-libero10 Model (based on [Haozhan72/Openvla-oft-SFT-libero10-traj1]((https://huggingface.co/Haozhan72/Openvla-oft-SFT-libero10-traj1)))
  - Recommended sampling settings:  `temperature = 1.6`, `top_p = 1.0`

### Benchmark Results

All sft models are from [SimpleVLA-RL](https://huggingface.co/collections/Haozhan72/simplevla-rl-6833311430cd9df52aeb1f86). 
  - Recommended sampleing setting for evaluation: `libero seed=0`; `episode number=500`; `do_sample=False`

| Model              | Object | Spatial | Goal  | Long  | Average |
| ------------------ | ------ | ------- | ----- | ----- | ------- |
| sft models         | 25.60  | 56.45   | 45.59 | 9.68  | 34.33   | 
| trained with RLinf | 98.99  | 98.99   | 98.99 | 94.35 | 97.83   | 

<div align="center">
  <img src="tensorboard-success_once.png" alt="RLinf-libero-result" width="600"/>
</div>

## How to Use
Please integrate the provided model with the [RLinf](https://github.com/RLinf/RLinf) codebase. To do so, modify the following parameters in the configuration file ``examples/embodiment/config/libero_spatial_grpo_openvlaoft.yaml``:

- Set ``actor.checkpoint_load_path``,  ``actor.tokenizer.tokenizer_model``, and ``rollout.model_dir`` to the path of the model checkpoint.

Note: If you intend to evaluate the model directly, make sure to set ``actor.model.is_lora`` to ``false``.

## License
This code repository and the model weights are licensed under the MIT License.