|
|
|
|
|
|
|
|
|
|
|
|
|
|
@@ -240,14 +240,14 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "code", |
|
|
- "source": [ |
|
|
- "!pip install sample-factory==2.1.1" |
|
|
- ], |
|
|
+ "execution_count": null, |
|
|
"metadata": { |
|
|
"id": "alxUt7Au-O8e" |
|
|
}, |
|
|
- "execution_count": null, |
|
|
- "outputs": [] |
|
|
+ "outputs": [], |
|
|
+ "source": [ |
|
|
+ "!pip install sample-factory==2.1.1" |
|
|
+ ] |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
@@ -260,7 +260,7 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "code", |
|
|
- "execution_count": null, |
|
|
+ "execution_count": 1, |
|
|
"metadata": { |
|
|
"id": "bCgZbeiavcDU" |
|
|
}, |
|
|
@@ -352,7 +352,24 @@ |
|
|
"metadata": { |
|
|
"id": "y_TeicMvyKHP" |
|
|
}, |
|
|
- "outputs": [], |
|
|
+ "outputs": [ |
|
|
+ { |
|
|
+ "name": "stderr", |
|
|
+ "output_type": "stream", |
|
|
+ "text": [ |
|
|
+ "\u001b[36m[2025-08-24 18:32:35,257][22314] register_encoder_factory: <function make_vizdoom_encoder at 0x7fed145c0220>\u001b[0m\n", |
|
|
+ "\u001b[33m[2025-08-24 18:32:35,271][22314] Saved parameter configuration for experiment default_experiment not found!\u001b[0m\n", |
|
|
+ "\u001b[33m[2025-08-24 18:32:35,273][22314] Starting experiment from scratch!\u001b[0m\n", |
|
|
+ "\u001b[36m[2025-08-24 18:32:35,283][22314] Experiment dir /home/luckye/_DevelopmentCode/RL_Boot/train_dir/default_experiment already exists!\u001b[0m\n", |
|
|
+ "\u001b[36m[2025-08-24 18:32:35,284][22314] Resuming existing experiment from /home/luckye/_DevelopmentCode/RL_Boot/train_dir/default_experiment...\u001b[0m\n", |
|
|
+ "\u001b[36m[2025-08-24 18:32:35,285][22314] Weights and Biases integration disabled\u001b[0m\n", |
|
|
+ "\u001b[36m[2025-08-24 18:32:38,518][22314] Queried available GPUs: 0\n", |
|
|
+ "\u001b[0m\n", |
|
|
+ "\u001b[37m\u001b[1m[2025-08-24 18:32:38,519][22314] Environment var CUDA_VISIBLE_DEVICES is 0\n", |
|
|
+ "\u001b[0m\n" |
|
|
+ ] |
|
|
+ } |
|
|
+ ], |
|
|
"source": [ |
|
|
"## 开始训练，这大约需要 15 分钟\n", |
|
|
"register_vizdoom_components()\n", |
|
|
@@ -418,12 +435,12 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
- "source": [ |
|
|
- "智能体学到了一些东西，但它的表现还可以更好。我们显然需要训练更长的时间。不过，让我们先把这个模型上传到 Hub。" |
|
|
- ], |
|
|
"metadata": { |
|
|
"id": "2A4pf_1VwPqR" |
|
|
- } |
|
|
+ }, |
|
|
+ "source": [ |
|
|
+ "智能体学到了一些东西，但它的表现还可以更好。我们显然需要训练更长的时间。不过，让我们先把这个模型上传到 Hub。" |
|
|
+ ] |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
@@ -495,14 +512,14 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
+ "metadata": { |
|
|
+ "id": "9PzeXx-qxVvw" |
|
|
+ }, |
|
|
"source": [ |
|
|
"## 让我们加载另一个模型\n", |
|
|
"\n", |
|
|
"\n" |
|
|
- ], |
|
|
- "metadata": { |
|
|
- "id": "9PzeXx-qxVvw" |
|
|
- } |
|
|
+ ] |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
@@ -568,16 +585,16 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
+ "metadata": { |
|
|
+ "id": "ie5YWC3NyKO8" |
|
|
+ }, |
|
|
"source": [ |
|
|
"## 一些额外挑战 🏆：Doom 死亡竞赛\n", |
|
|
"\n", |
|
|
"训练一个能玩 Doom 死亡竞赛的智能体**需要在一台比 Colab 中可用机器配置更强的机器上花费数小时**。\n", |
|
|
"\n", |
|
|
"幸运的是，我们**已经在这个场景中训练好了一个智能体，并且它可以在 🤗 Hub 上找到！** 让我们下载模型并可视化智能体的表现。" |
|
|
- ], |
|
|
- "metadata": { |
|
|
- "id": "ie5YWC3NyKO8" |
|
|
- } |
|
|
+ ] |
|
|
}, |
|
|
{ |
|
|
"cell_type": "code", |
|
|
@@ -593,12 +610,12 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
- "source": [ |
|
|
- "由于智能体游戏时间很长，视频生成可能需要**10分钟**。" |
|
|
- ], |
|
|
"metadata": { |
|
|
"id": "7AX_LwxR2FQ0" |
|
|
- } |
|
|
+ }, |
|
|
+ "source": [ |
|
|
+ "由于智能体游戏时间很长，视频生成可能需要**10分钟**。" |
|
|
+ ] |
|
|
}, |
|
|
{ |
|
|
"cell_type": "code", |
|
|
@@ -625,17 +642,20 @@ |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
+ "metadata": { |
|
|
+ "id": "N6mEC-4zyihx" |
|
|
+ }, |
|
|
"source": [ |
|
|
"\n", |
|
|
"您**可以尝试使用上面的代码在这个环境中训练您的智能体**，但不能在 Colab 上进行。\n", |
|
|
"**祝您好运 🤞**" |
|
|
- ], |
|
|
- "metadata": { |
|
|
- "id": "N6mEC-4zyihx" |
|
|
- } |
|
|
+ ] |
|
|
}, |
|
|
{ |
|
|
"cell_type": "markdown", |
|
|
+ "metadata": { |
|
|
+ "id": "YnDAngN6zeeI" |
|
|
+ }, |
|
|
"source": [ |
|
|
"如果您喜欢更简单的场景，**为什么不尝试在另一个 ViZDoom 场景中进行训练，例如 `doom_deadly_corridor` 或 `doom_defend_the_center`。**\n", |
|
|
"\n", |
|
|
@@ -647,33 +667,40 @@ |
|
|
"最后一个单元到此结束。但我们还没有完！ 🤗 接下来的**附加部分将包含深度强化学习中一些最有趣、最前沿和最尖端的工作**。\n", |
|
|
"\n", |
|
|
"## 保持学习，保持出色 🤗" |
|
|
- ], |
|
|
- "metadata": { |
|
|
- "id": "YnDAngN6zeeI" |
|
|
- } |
|
|
+ ] |
|
|
} |
|
|
], |
|
|
"metadata": { |
|
|
"accelerator": "GPU", |
|
|
"colab": { |
|
|
- "provenance": [], |
|
|
"collapsed_sections": [ |
|
|
"PU4FVzaoM6fC", |
|
|
"nB68Eb9UgC94", |
|
|
"ez5UhUtYcWXF", |
|
|
"sgRy6wnrgnij" |
|
|
], |
|
|
- "private_outputs": true |
|
|
+ "private_outputs": true, |
|
|
+ "provenance": [] |
|
|
}, |
|
|
"gpuClass": "standard", |
|
|
"kernelspec": { |
|
|
- "display_name": "Python 3", |
|
|
+ "display_name": "Python 3 (ipykernel)", |
|
|
+ "language": "python", |
|
|
"name": "python3" |
|
|
}, |
|
|
"language_info": { |
|
|
- "name": "python" |
|
|
+ "codemirror_mode": { |
|
|
+ "name": "ipython", |
|
|
+ "version": 3 |
|
|
+ }, |
|
|
+ "file_extension": ".py", |
|
|
+ "mimetype": "text/x-python", |
|
|
+ "name": "python", |
|
|
+ "nbconvert_exporter": "python", |
|
|
+ "pygments_lexer": "ipython3", |
|
|
+ "version": "3.12.3" |
|
|
} |
|
|
}, |
|
|
"nbformat": 4, |
|
|
"nbformat_minor": 0 |
|
|
-} |
|
|
\ No newline at end of file |
|
|
+} |
|
|
|
