ONNX 模型库
返回模型

说明文档

ppo 智能体玩 SnowballTarget

这是一个训练好的 ppo 智能体，使用 Unity ML-Agents Library 玩 SnowballTarget。

使用方法（配合 ML-Agents）

文档地址：https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/

我们编写了完整的教程，教你如何使用 ML-Agents 训练你的第一个智能体并发布到 Hub：

  • 一个简短教程，教你训练 Huggy 小狗 🐶 去捡树枝，然后直接在浏览器中和它玩耍：https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
  • 一个更长的教程，帮助你深入理解 ML-Agents 的工作原理：https://huggingface.co/learn/deep-rl-course/unit5/introduction

继续训练

mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume

观看你的智能体玩耍

你可以直接在浏览器中观看你的智能体玩耍

  1. 如果该环境是 ML-Agents 官方环境的一部分，请访问 https://huggingface.co/unity
  2. 第一步：找到你的 model_id：Momin-Shahzad/ppo-SnowballTarget
  3. 第二步：选择你的 .nn /.onnx 文件
  4. 点击"Watch the agent play 👀"

Momin-Shahzad/ppo-SnowballTarget

作者 Momin-Shahzad

reinforcement-learning ml-agents
↓ 0 ♥ 0

创建时间: 2025-05-04 12:13:31+00:00

更新时间: 2025-05-04 12:13:34+00:00

在 Hugging Face 上查看

文件 (30)

.gitattributes
README.md
SnowballTarget.onnx ONNX
SnowballTarget/SnowballTarget-119952.onnx ONNX
SnowballTarget/SnowballTarget-119952.pt
SnowballTarget/SnowballTarget-129992.onnx ONNX
SnowballTarget/SnowballTarget-129992.pt
SnowballTarget/SnowballTarget-139944.onnx ONNX
SnowballTarget/SnowballTarget-139944.pt
SnowballTarget/SnowballTarget-149984.onnx ONNX
SnowballTarget/SnowballTarget-149984.pt
SnowballTarget/SnowballTarget-159936.onnx ONNX
SnowballTarget/SnowballTarget-159936.pt
SnowballTarget/SnowballTarget-169976.onnx ONNX
SnowballTarget/SnowballTarget-169976.pt
SnowballTarget/SnowballTarget-179992.onnx ONNX
SnowballTarget/SnowballTarget-179992.pt
SnowballTarget/SnowballTarget-189968.onnx ONNX
SnowballTarget/SnowballTarget-189968.pt
SnowballTarget/SnowballTarget-199984.onnx ONNX
SnowballTarget/SnowballTarget-199984.pt
SnowballTarget/SnowballTarget-200112.onnx ONNX
SnowballTarget/SnowballTarget-200112.pt
SnowballTarget/checkpoint.pt
SnowballTarget/events.out.tfevents.1746360031.de607150c00d.4434.0
config.json
configuration.yaml
run_logs/Player-0.log
run_logs/timers.json
run_logs/training_status.json