Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- ml-agents
|
| 4 |
+
- deep-reinforcement-learning
|
| 5 |
+
- reinforcement-learning
|
| 6 |
+
- unity-ml-agents
|
| 7 |
+
library_name: ml-agents
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
# ML-Agents 训练展示：SnowballTarget
|
| 11 |
+
|
| 12 |
+
这是使用 Unity ML-Agents 训练的 **SnowballTarget** 模型。
|
| 13 |
+
|
| 14 |
+
### 训练效果展示
|
| 15 |
+
<div align="center">
|
| 16 |
+
<video src="https://huggingface.co/LuckLin/ppo-SnowballTarget/resolve/main/replay.mp4" controls autoplay loop muted width="600"></video>
|
| 17 |
+
</div>
|
| 18 |
+
|
| 19 |
+
### 训练说明
|
| 20 |
+
- **算法**: PPO
|
| 21 |
+
- **运行 ID**: `SnowballTarget1`
|
| 22 |
+
- **训练环境**: SnowballTarget
|
| 23 |
+
|
| 24 |
+
### 如何使用
|
| 25 |
+
你可以下载本项目中的 `results/SnowballTarget1` 文件夹，并将其放入 Unity 项目中进行推理。
|