---
title: hands-on-modern-rl-experiment06-minigrid-adventure
canonical_url: "https://www.modelscope.cn/studios/walkinglab/hands-on-modern-rl-experiment06-minigrid-adventure"
md_url: "https://www.modelscope.cn/studios/walkinglab/hands-on-modern-rl-experiment06-minigrid-adventure.md"
repository: walkinglab/hands-on-modern-rl-experiment06-minigrid-adventure
chinese_name: "Experiment 06 · MiniGrid Adventures"
last_updated: 2026-08-20
sdk_type: gradio
sdk_version: 6.17.3
downloads: 0
stars: 0
---

# hands-on-modern-rl-experiment06-minigrid-adventure

> hands-on-modern-rl-experiment06-minigrid-adventure - walkinglab 在 ModelScope 创建的在线 Demo。Hands-On Modern RL 配套实验：在门、钥匙和障碍迷宫中训练探索策略。

walkinglab/hands-on-modern-rl-experiment06-minigrid-adventure 是 ModelScope 魔搭社区上的在线可交互 Demo（创空间），基于 gradio 6.17.3 构建，中文名为「Experiment 06 · MiniGrid Adventures」。

- **Repository**: walkinglab/hands-on-modern-rl-experiment06-minigrid-adventure
- **SDK**: gradio
- **SDK version**: 6.17.3
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-08-20

Source: https://www.modelscope.cn/studios/walkinglab/hands-on-modern-rl-experiment06-minigrid-adventure

---

# WalkingLab × Hands-On Modern RL · MiniGrid Exploration Adventures

**WalkingLab** 与开源课程 **Hands-On Modern RL（《动手学现代强化学习》）** 的探索实验。在 ModelScope CPU 容器中训练 MiniGrid 探索策略。页面展示实时 PPO 评估、训练日志和当前运行生成的完整迷宫回放。

课程项目：<https://github.com/walkinglabs/hands-on-modern-rl>

WalkingLab：<https://modelscope.cn/organization/walkinglab>

## 配套实验 Notebook

[直接在 ModelScope Notebook 中运行 MiniGrid 实验](https://modelscope.cn/notebook/share/github/walkinglabs/hands-on-modern-rl/blob/main/code/online-experiments/hands-on-modern-rl-experiment06-minigrid-adventure.ipynb)。Notebook 与当前创空间复用同一份探索训练运行时，并显示完整日志、评估曲线和迷宫策略回放。
