Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of Diffusion Model in RL resources (continually updated)
| Date | Stars |
|---|---|
| 2026-07-31 | 1631 |
| 2026-08-02 | 1631 |
| 2026-08-06 | 1631 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
# Awesome Diffusion Model in RL
[](https://github.com/sindresorhus/awesome) [](https://github.com/opendilab/awesome-diffusion-model-in-rl)    [](https://github.com/opendilab/awesome-diffusion-model-in-rl/blob/main/LICENSE)
This is a collection of research papers for **Diffusion Model in RL**.
And the repository will be continuously updated to track the frontier of Diffusion RL.
Welcome to follow and star!
## Table of Contents
- [Awesome Diffusion Model in RL](#awesome-diffusion-model-in-rl)
- [Table of Contents](#table-of-contents)
- [Overview of Diffusion Model in RL](#overview-of-diffusion-model-in-rl)
- [Advantage](#advantage)
- [Papers](#papers)
- [Arxiv](#arxiv)
- [ICML 2026](#icml-2026)
- [ICLR 2026](#iclr-2026)
- [NeurIPS 2025](#neurips-2025)
- [ICML 2025](#icml-2025)
- [ICLR 2025](#iclr-2025)
- [NeurIPS 2024](#neurips-2024)
- [ICML 2024](#icml-2024)
- [CVPR 2024](#cvpr-2024)
- [ICLR 2024](#iclr-2024)
- [NeurIPS 2023](#neurips-2023)
- [ICML 2023](#icml-2023)
- [ICLR 2023](#iclr-2023)
- [ICRA 2023](#icra-2023)
- [NeurIPS 2022](#neurips-2022)
- [ICML 2022](#icml-2022)
- [Codebase](#codebase)
- [Contributing](#contributing)
- [License](#license)
## Overview of Diffusion Model in RL
The Diffusion Model in RL was introduced by “Planning with Diffusion for Flexible Behavior Synthesis” by Janner, Michael, et al. It casts trajectory optimization as a **diffusion probabilistic model** that plans by iteratively refining trajectories.
There is another way: "Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning" by Wang, Z. proposed Diffusion Model as policy-optimization in offline RL, et al. Specifically, Diffusion-QL forms policy as a conditional diffusion model with states as the condition from the offline policy-optimization perspective.
### Advantage
1. Bypass the need for bootstrapping for long term credit assignment.
2. Avoid undesirable short-sighted behaviors due to the discounting future rewards.
3. Enjoy the diffusion models widely used in language and vision, which are easy to scale and adapt to multi-modal data.
## Papers
```
format:
- [title](paper link) [links]
- author1, author2, and author3...
- publisher
- key
- code
- experiment environment
```
### Arxiv
- [Flow-Based Single-Step Completion for Efficient and Expressive Policy Learning](https://arxiv.org/abs/2506.21427)
- Prajwal Koirala, Cody Fleming
- Key: Offline RL, Flow Matching, Behavior Cloning, Goal-Conditioned RL, Shortcut Models
- ExpEnv: D4RL, OGBench, Robomimic
- [Enhancing Memory and Imagination Consistency in Diffusion-based World Models via Linear-Time Sequence Modeling](https://www.arxiv.org/abs/2502.00466)
- Jia-Hua Lee, Bor-Jiun Lin, Wei-Fang Sun, Chun-Yi Lee
- Key: Reinforcement Learning, Model-Based Reinforcement Learning, Diffusion Models, Selective State Spaces
- ExpEnv: Atari 100k Benchmark, ViZDoom, MiniGrid
- [Enhancing Deep Reinforcement Learning: A Tutorial on Generative Diffusion Models in Network Optimization](https://arxiv.org/abs/2308.05384)
- Hongyang Du, Ruichen Zhang, Yinqiu Liu, Jiacheng Wang, Yijing Lin, Zonghang Li, Dusit Niyato, Jiawen Kang, Zehui Xiong, Shuguang Cui, Bo Ai, Haibo Zhou, Dong In Kim
- Key: Generative Diffusion ModeExcerpt of 41,595 characters
Read on GitHub
CloudChen
11
8
蒲源 · China · China
3
3
2
1
1
1
1
1
1
1
1
1
1
Chen-Hao (Leo) Chang · @Tencent-Hunyuan, @OpenDILab, @vision-x-nyu, HUST · United States
1
Swain · @opendilab · China
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:03d264a4ad903f93, topic:diffusion-models, name:diffusion model, desc:diffusion model
matched fp:03d264a4ad903f93, topic:deep-reinforcement-learning