|
62 | 62 | with: |
63 | 63 | tag_name: ${{ github.ref_name }} |
64 | 64 | name: "Release ${{ github.ref_name }}" |
65 | | - body: "📦 各模块独立下载包(含README和说明图):" |
| 65 | + body: | # 👇 这里已经更新为优化后的双语发布说明 |
| 66 | + # 多模块独立发布包 |
| 67 | +
|
| 68 | + ## 模块介绍 |
| 69 | + - 🚀 **MADDPG_Continous** |
| 70 | + 多智能体深度确定性策略梯度算法(连续动作空间版本),适用于连续控制场景的多智能体协同训练。 |
| 71 | +
|
| 72 | + - ⚡️ **MATD3_Continous** |
| 73 | + 多智能体双延迟深度确定性策略梯度算法,在MADDPG基础上增加了延迟更新和策略平滑机制。 |
| 74 | +
|
| 75 | + - 📚 **RL_Learning-main** |
| 76 | + 赵世钰老师强化学习基础教程合集,包含经典算法实现和示例代码。 |
| 77 | +
|
| 78 | + - **hands_on_RL** |
| 79 | + 动手学强化学习实践项目,通过Jupyter Notebook提供互动式学习体验。 |
| 80 | +
|
| 81 | + ## 使用说明 |
| 82 | + 1. 点击下方所需模块的ZIP文件下载 |
| 83 | + 2. 解压后阅读README.md获取详细使用指南 |
| 84 | + 3. 安装依赖:`pip install -r requirements.txt` |
| 85 | +
|
| 86 | + ## 支持渠道 |
| 87 | + - [中文问题提交](https://github.com/Ronchy2000/Multi-agent-RL/issues/new?labels=zh) |
| 88 | + - 许可证:[MIT](LICENSE) |
| 89 | +
|
| 90 | + --- |
| 91 | +
|
| 92 | + # Independent Modules Release |
| 93 | +
|
| 94 | + ## Available Modules |
| 95 | + - **MADDPG_Continous** |
| 96 | + Multi-Agent Deep Deterministic Policy Gradient (continuous action space version) for cooperative multi-agent control. |
| 97 | +
|
| 98 | + - ️ **MATD3_Continous** |
| 99 | + Multi-Agent Twin Delayed DDPG, featuring delayed updates and policy smoothing. |
| 100 | +
|
| 101 | + - 📚 **RL_Learning-main** |
| 102 | + Fundamental RL tutorials with classic algorithm implementations. |
| 103 | +
|
| 104 | + - 🧠 **hands_on_RL** |
| 105 | + Interactive reinforcement learning projects via Jupyter Notebooks. |
| 106 | +
|
| 107 | + ## Quick Start |
| 108 | + 1. Download the desired module ZIP below |
| 109 | + 2. Check README_en.md for detailed instructions |
| 110 | + 3. Install dependencies: `pip install -r requirements.txt` |
| 111 | +
|
| 112 | + ## Support |
| 113 | + - [English Issues](https://github.com/Ronchy2000/Multi-agent-RL/issues/new?labels=en) |
| 114 | + - License: [MIT](LICENSE) |
66 | 115 | files: | |
67 | 116 | zips/*.zip |
68 | 117 | env: |
|
0 commit comments