Upload models via script
Browse files- DQN-base.pth +3 -0
- README.md +35 -0
- alpha-zero-high.pth +3 -0
- alpha-zero-medium.pth +3 -0
DQN-base.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cfe71d357b7f2305c18f85bb9e14ec9fc53d533645038f3520e825df3670fd4c
|
| 3 |
+
size 6548638
|
README.md
CHANGED
|
@@ -1,3 +1,38 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
tags:
|
| 4 |
+
- reinforcement-learning
|
| 5 |
+
- connectx
|
| 6 |
+
- kaggle
|
| 7 |
+
- game-ai
|
| 8 |
---
|
| 9 |
+
|
| 10 |
+
# Kaggle ConnectX Models
|
| 11 |
+
|
| 12 |
+
这个仓库包含了用于 Kaggle ConnectX 竞赛的强化学习模型
|
| 13 |
+
|
| 14 |
+
## 模型文件
|
| 15 |
+
|
| 16 |
+
- `alpha-zero-high.pth`: AlphaZero 高性能模型
|
| 17 |
+
- `alpha-zero-medium.pth`: AlphaZero 中等性能模型
|
| 18 |
+
- `DQN-base.pth`: Deep Q-Network 基础模型
|
| 19 |
+
|
| 20 |
+
## 使用方法
|
| 21 |
+
|
| 22 |
+
```python
|
| 23 |
+
import torch
|
| 24 |
+
|
| 25 |
+
# 加载模型
|
| 26 |
+
model = torch.load('alpha-zero-high.pth')
|
| 27 |
+
model.eval()
|
| 28 |
+
```
|
| 29 |
+
|
| 30 |
+
## 模型说明
|
| 31 |
+
|
| 32 |
+
### AlphaZero Models
|
| 33 |
+
|
| 34 |
+
基于 AlphaZero 算法的模型,使用蒙特卡洛树搜索(MCTS)和深度神经网络。
|
| 35 |
+
|
| 36 |
+
### DQN Model
|
| 37 |
+
|
| 38 |
+
基于 Deep Q-Network 的强化学习模型。
|
alpha-zero-high.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5823c5ab13cd9f4e8785e19e628a891240a5b812b961a375f8b261a17dfe7545
|
| 3 |
+
size 124719787
|
alpha-zero-medium.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebde4f881bab326ce89d2aeabffb2063db0c87cb9456f15131b066011307da86
|
| 3 |
+
size 22979360
|