https://github.com/chendrag/cep-energy-guided-diffusion

Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction （ICML 2023）
https://github.com/chendrag/cep-energy-guided-diffusion

cep diffusion energy guided offline qgpo reinforcement-learning sampling

Last synced: 2 months ago
JSON representation

Official codebase for Exact Energy-Guided Diffusion Sampling via Contrastive Energy Prediction （ICML 2023）

• Host: GitHub
• URL: https://github.com/chendrag/cep-energy-guided-diffusion
• Owner: ChenDRAG
• License: mit
• Created: 2023-03-31T14:20:26.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2023-08-26T06:47:50.000Z (over 1 year ago)
• Last Synced: 2025-03-18T11:11:25.530Z (2 months ago)
• Topics: cep, diffusion, energy, guided, offline, qgpo, reinforcement-learning, sampling
• Language: Python
• Homepage:
• Size: 3.53 MB
• Stars: 46
• Watchers: 1
• Forks: 8
• Open Issues: 1
• Metadata Files:
  • Readme: Readme.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Contrastive Energy Prediction

Official codebase for [Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning](https://arxiv.org/abs/2304.12824).

Contains scripts to reproduce experiments.

Cheng Lu\*, Huayu Chen\*, Jianfei Chen†, Hang Su, Chongxuan Li, Jun Zhu†

\*equal contribution, †equal advising

![image info](./title_figure.PNG)

## Instructions

We provide code in two sub-directories: `Offline_RL_2D` containing code for example toy 2D and offline RL experiments and `images` containing code (based on implementations of [openai/guided-diffusion](https://github.com/openai/guided-diffusion)) for Imagenet experiments.

See corresponding READMEs in each folder for instructions; scripts should be run from the respective directories.

## Citation

Please cite our paper as:

```

@article{lu2023contrastive,

  title={Contrastive Energy Prediction for Exact Energy-Guided Diffusion Sampling in Offline Reinforcement Learning},

  author={Lu, Cheng and Chen, Huayu and Chen, Jianfei and Su, Hang and Li, Chongxuan and Zhu, Jun},

  journal={arXiv preprint arXiv:2304.12824},

  year={2023}

}

```

## License

MIT