README.md

---
license: mit
---

# eVTA₀ Models

This repository hosts the released checkpoints of the paper
["Demonstration-Free Success-Probability Reward Learning for Generalist Robot
Policies"](https://arxiv.org/abs/2609.33653).

- **Reward models** (`reward_model/`): the eVTA₀ success-probability reward
  model trained on LIBERO and MetaWorld rollouts (`checkpoint_adapter.pth`).
  The checkpoints contain only the LoRA adapter, the reward-token embedding,
  and the prediction head — the backbone is not included; download
  [Qwen/Qwen3-VL-4B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-4B-Instruct)
  separately and load the checkpoint on top of it. These checkpoints were
  serialized under transformers 5.8.0 / peft 0.19.1; loading them requires
  `transformers >= 5.8.0` and `peft >= 0.19.1`.
- **RL policies** (`pi05_policy/`): pi0.5 policies trained with GRPO driven by
  the eVTA₀ reward, one per LIBERO suite
  (`evta0-grpo-6400ep-{suite}-pi05.pt`).


**Code:** https://github.com/duowuyms/eVTA0

**Paper:** https://arxiv.org/abs/2609.33653

**Author:** [Duo Wu](https://duowuyms.github.io/)

## Citation

If you find these models useful, please cite our paper:

```bibtex
@article{wu2026evta0,
  title={Demonstration-Free Success-Probability Reward Learning for Generalist Robot Policies},
  author={Wu, Duo and Wang, Haifeng and Lu, Rongwei and Wang, Jinghe and Xiong, Tianyi and Wang, Zhimin and Yu, Chao and Ma, Shuai and Wang, Zhi},
  journal={arXiv preprint arXiv:2609.33653},
  year={2026}
}
```