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.
[NeurIPS 2023 Spotlight] LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios (awesome MCTS)
| Date | Stars |
|---|---|
| 2026-07-24 | 1625 |
| 2026-07-25 | 1625 |
| 2026-07-28 | 1626 |
| 2026-07-30 | 1626 |
| 2026-08-06 | 1626 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div id="top"></div>
# LightZero
<div align="center">
<img width="1000px" height="auto" src="https://github.com/opendilab/LightZero/blob/main/LightZero.png"></a>
</div>
---
[](https://twitter.com/opendilab)
[](https://pypi.org/project/LightZero/)
[](https://github.com/opendilab/LightZero/actions?query=workflow%3A%22Code+Test%22)
[](https://github.com/opendilab/LightZero/actions?query=workflow%3A%22Badge+Creation%22)
[](https://github.com/opendilab/LightZero/actions?query=workflow%3A%22Package+Release%22)
[](https://github.com/opendilab/LightZero/stargazers)
[](https://github.com/opendilab/LightZero/network)
[](https://github.com/opendilab/LightZero/issues)
[](https://github.com/opendilab/LightZero/pulls)
[](https://github.com/opendilab/LightZero/graphs/contributors)
[](https://github.com/opendilab/LightZero/blob/master/LICENSE)
[](https://discord.gg/dkZS2JF56X)
Updated on 2026.03.11 LightZero-v0.2.0
> LightZero is a lightweight, efficient, and easy-to-understand open-source algorithm toolkit that combines Monte Carlo Tree Search (MCTS) and Deep Reinforcement Learning (RL).
English | [简体中文(Simplified Chinese)](https://github.com/opendilab/LightZero/blob/main/README.zh.md) | [Documentation](https://opendilab.github.io/LightZero) | [LightZero Paper](https://arxiv.org/abs/2310.08348) | [UniZero Paper](https://openreview.net/forum?id=Gl6dF9soQo) | [ReZero Paper](https://openreview.net/forum?id=F9Y7j3AJTu) | [🔥ScaleZero Paper](https://arxiv.org/abs/2509.07945)
## News
- [2026.02] 🔥 The ScaleZero paper has been accepted as a conference paper at ICLR 2026: [One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning](https://arxiv.org/abs/2509.07945).
- [2025.08] The [ReZero paper](https://openreview.net/forum?id=F9Y7j3AJTu) has been accepted by the CoRL 2025 RemembeRL workshop.
- [2025.06] The [UniZero paper](https://openreview.net/forum?id=Gl6dF9soQo) has been accepted by Transactions on Machine Learning Research (TMLR 2025).
- [2023.09] The [LightZero paper](https://proceedings.neurips.cc/paper_files/paper/2023/hash/765043fe026f7d704c96cec027f13843-Abstract-Datasets_and_Benchmarks.html) has been accepted as a Spotlight Presentation at the NeurIPS 2023 Datasets and Benchmarks Track.
- [2023.04] LightZero v0.0.1 was officially released.
## 🔍 Background
The integration of Monte Carlo Tree Search and Deep Reinforcement Learning,
exemplified by AlphaZero and MuZero,
has achieved unprecedented performance levels in various games, including Go and Atari.
This advaExcerpt of 57,783 characters
Read on GitHub
蒲源 · China · China
185
Norman · @OpenDILab · China
14
11
8
Swain · @opendilab · China
7
6
5
Zhenjie Yang · Postdoc@HKU, PhD@SJTU · Hong Kong
5
Mr_TJ
3
2
Mohit Dhote · India
2
2
Hankson Bradley · Beihang University · China
2
Prajjwal Yadav · @Weaviate · India
2
2
2
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:a638cdad1beb69f6, topic:reinforcement-learning, readme:reinforcement learning
matched fp:a638cdad1beb69f6, topic:pytorch