---
license: cc-by-nc-4.0
---

This repository contains model checkpoints for [**Generative OOD-regularized Model-based Policy Optimization (GORMPO)**](https://openreview.net/forum?id=3KDoYUU2CU) on author-created sparse medium-expert level D4RL datasets from the Gym environment: halfcheetah, walker2d and hopper.

Each folder contains density model checkpoints (KDE, VAE, RealNVP, Diffusion, NeuralODE) and policy checkpoints for MBPO-based (mbpo_based) and MOBILE-based (mobile_based) GORMPO. Each policy folder contains policies that are trained with each density model's reward penalty.

## Usage

Clone the [GORMPO codebase](https://github.com/Rose-STL-Lab/GORMPO), download the models, and follow the instructions in the README. See the datasets [here](https://huggingface.co/datasets/aysin/sparse_medium_expert_D4RL). 

## Citation


If you find this repository useful for your research, please cite:

```bibtex
@inproceedings{tumay2026gormpo,
    title={Generative {OOD}-regularized Model-based Policy Optimization},
    author={Tumay, Aysin and Huang, Jiahe and Jortberg, Elise and Yu, Rose},
    booktitle={Advances in Neural Information Processing Systems},
    year={2026},
    url={https://openreview.net/forum?id=3KDoYUU2CU}
}
```