# sail-sg/gdpo

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/sail-sg-gdpo).**

43 stars · 5 forks · Python

## Links

- GitHub: https://github.com/sail-sg/GDPO
- awesome-repositories: https://awesome-repositories.com/repository/sail-sg-gdpo.md

## Description

This paper introduces $\textit{graph diffusion policy optimization}$ (GDPO), a novel approach to optimize graph diffusion models for arbitrary (e.g., non-differentiable) objectives using reinforcement learning. GDPO is based on an $\textit{eager policy gradient}$ tailored for graph diffusion…

## Tags

### Part of an Awesome List

- [Offline Reinforcement Learning](https://awesome-repositories.com/f/awesome-lists/ai/offline-reinforcement-learning.md) — Optimizing policies through graph-based diffusion generative processes.