Skip to content

Commit

Permalink
polish(pu): update the supported env and algo list (#96)
Browse files Browse the repository at this point in the history 
* polish(pu): update the supported env and algo list

* polish(pu): update zoo/README.md
  • Loading branch information
@puyuan1996
puyuan1996 authored Sep 15, 2023
1 parent 9c42878 commit d28d6c5
Show file tree
Hide file tree
Showing 3 changed files with 61 additions and 44 deletions.
33 changes: 19 additions & 14 deletions README.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -108,34 +108,39 @@ For the file structure of LightZero, please refer to [lightzero_file_structure](
LightZero is a library with a [PyTorch](https://pytorch.org/) implementation of MCTS algorithms (sometimes combined with cython and cpp), including:
- [AlphaZero](https://www.science.org/doi/10.1126/science.aar6404)
- [MuZero](https://arxiv.org/abs/1911.08265)
- [EfficientZero](https://arxiv.org/abs/2111.00210)
- [Sampled MuZero](https://arxiv.org/abs/2104.06303)
- [Stochastic MuZero](https://openreview.net/pdf?id=X6D9bAHhBQ1)
- [EfficientZero](https://arxiv.org/abs/2111.00210)
- [Gumbel MuZero](https://openreview.net/pdf?id=bERaNdoegnO&)

The environments and algorithms currently supported by LightZero are shown in the table below:

| Env./Alg. | AlphaZero | MuZero | EfficientZero | Sampled EfficientZero | Gumbel MuZero |
| ------------- | --------- | ------ | ------------- | --------------------- | ------------- |
| Atari | --- | ✔ | ✔ | ✔ | ✔ |
| TicTacToe | ✔ | ✔ | 🔒 | 🔒 | ✔ |
| Gomoku | ✔ | ✔ | 🔒 | 🔒 | ✔ |
| Go | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |
| LunarLander | --- | ✔ | ✔ | ✔ | ✔ |
| BipedalWalker | --- | ✔ | ✔ | ✔ | 🔒 |
| CartPole | --- | ✔ | ✔ | ✔ | ✔ |
| Pendulum | --- | ✔ | ✔ | ✔ | ✔ |
| MuJoCo | --- | 🔒 | 🔒 | ✔ | 🔒 |
| Env./Algo. | AlphaZero | MuZero | EfficientZero | Sampled EfficientZero | Gumbel MuZero | Stochastic MuZero |
|---------------| --------- | ------ |-------------| ------------------ | ---------- |----------------|
| TicTacToe | ✔ | ✔ | 🔒 | 🔒 | ✔ | 🔒 |
| Gomoku | ✔ | ✔ | 🔒 | 🔒 | ✔ | 🔒 |
| Connect4 | ✔ | ✔ | 🔒 | 🔒 | 🔒 | 🔒 |
| 2048 | ✔ | ✔ | 🔒 | 🔒 | 🔒 | ✔ |
| Chess | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |
| Go | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |
| CartPole | --- | ✔ | ✔ | ✔ | ✔ | ✔ |
| Pendulum | --- | ✔ | ✔ | ✔ | ✔ | 🔒 |
| LunarLander | --- | ✔ | ✔ | ✔ | ✔ | ✔ |
| BipedalWalker | --- | ✔ | ✔ | ✔ | ✔ | 🔒 |
| Atari | --- | ✔ | ✔ | ✔ | ✔ | ✔ |
| MuJoCo | --- | ✔ | ✔ | ✔ | 🔒 | 🔒 |
| MiniGrid | --- | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |

<sup>(1): "✔" means that the corresponding item is finished and well-tested.</sup>

<sup>(2): "🔒" means that the corresponding item is in the waitinglist (Work In Progress).</sup>
<sup>(2): "🔒" means that the corresponding item is in the waiting-list (Work In Progress).</sup>

<sup>(3): "---" means that this algorithm doesn't support this environment.</sup>


## Installation

You can install latest LightZero in development from the GitHub source codes with the following command:
You can install the latest LightZero in development from the GitHub source codes with the following command:

```bash
git clone https://github.com/opendilab/LightZero.git
Expand Down
31 changes: 18 additions & 13 deletions README.zh.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -97,24 +97,29 @@
LightZero 是基于 [PyTorch](https://pytorch.org/) 实现的 MCTS 算法库，在 MCTS 的实现中也用到了 cython 和 cpp。同时，LightZero 的框架主要基于 [DI-engine](https://github.com/opendilab/DI-engine) 实现。目前 LightZero 中集成的算法包括：
- [AlphaZero](https://www.science.org/doi/10.1126/science.aar6404)
- [MuZero](https://arxiv.org/abs/1911.08265)
- [EfficientZero](https://arxiv.org/abs/2111.00210)
- [Sampled MuZero](https://arxiv.org/abs/2104.06303)
- [Stochastic MuZero](https://openreview.net/pdf?id=X6D9bAHhBQ1)
- [EfficientZero](https://arxiv.org/abs/2111.00210)
- [Gumbel MuZero](https://openreview.net/pdf?id=bERaNdoegnO&)

LightZero 目前支持的环境及算法如下表所示：

| Env./Alg. | AlphaZero | MuZero | EfficientZero | Sampled EfficientZero | Gumbel MuZero |
|---------------| --------- |--------| ------- | --------------------- | ------------ |
| Atari | --- | ✔ | ✔ | ✔ | ✔ |
| TicTacToe | ✔ | ✔ | 🔒 | 🔒 | ✔ |
| Gomoku | ✔ | ✔ | 🔒 | 🔒 | ✔ |
| Go | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |
| LunarLander | --- | ✔ | ✔ | ✔ | ✔ |
| BipedalWalker | --- | ✔ | ✔ | ✔ | 🔒 |
| CartPole | --- | ✔ | ✔ | ✔ | ✔ |
| Pendulum | --- | ✔ | ✔ | ✔ | ✔ |
| MuJoCo | --- | 🔒 | 🔒 | ✔ | 🔒 |
LightZero 目前支持的环境及算法如下表所示：

| Env./Algo. | AlphaZero | MuZero | EfficientZero | Sampled EfficientZero | Gumbel MuZero | Stochastic MuZero |
|---------------| --------- | ------ |-------------| ------------------ | ---------- |----------------|
| TicTacToe | ✔ | ✔ | 🔒 | 🔒 | ✔ | 🔒 |
| Gomoku | ✔ | ✔ | 🔒 | 🔒 | ✔ | 🔒 |
| Connect4 | ✔ | ✔ | 🔒 | 🔒 | 🔒 | 🔒 |
| 2048 | ✔ | ✔ | 🔒 | 🔒 | 🔒 | ✔ |
| Chess | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |
| Go | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |
| CartPole | --- | ✔ | ✔ | ✔ | ✔ | ✔ |
| Pendulum | --- | ✔ | ✔ | ✔ | ✔ | 🔒 |
| LunarLander | --- | ✔ | ✔ | ✔ | ✔ | ✔ |
| BipedalWalker | --- | ✔ | ✔ | ✔ | ✔ | 🔒 |
| Atari | --- | ✔ | ✔ | ✔ | ✔ | ✔ |
| MuJoCo | --- | ✔ | ✔ | ✔ | 🔒 | 🔒 |
| MiniGrid | --- | 🔒 | 🔒 | 🔒 | 🔒 | 🔒 |

<sup>(1): "✔" 表示对应的项目已经完成并经过良好的测试。</sup>

Expand Down
Loading

0 comments on commit d28d6c5

Please sign in to comment.