参考内容
CodeMonkey - How to use Machine Learning AI in Unity! (ML-Agents)
Making a New Learning Environment
Unity官方Github地址和文档内容
Unity ML-Agents Toolkit Documentation
CodeMonkey 更多的关于UnityML的系列内容
Machine Learning AI in Unity (ML-Agents)
常见问题
安装python https://www.python.org/downloads/windows/
如果你的命令行输入不起作用？windows下命令行模式中cd命令无效的原因
关于pytorch是什么？
pytorch与tensorflow https://zhuanlan.zhihu.com/p/104842311
适合PyTorch小白的官网教程 https://zhuanlan.zhihu.com/p/271659551
An open source machine learning framework that accelerates the path from research prototyping to production deployment. https://pytorch.org/
如何最简单、通俗地理解Pytorch？ https://www.zhihu.com/question/439496333/answer/1715174511
你可以把 pytorch 理解为一个支持 gpu 的，可以进行求导的计算器。新添的这两个功能现在主要是给神经网络用的，所以 pytorch 里面也加了很多神经网络用的辅助工具
为什么需要安装Python虚拟机？
py的虚拟环境 A Virtual Environment is a self contained directory tree that contains a Python installation for a particular version of Python, plus a number of additional packages.
A Virtual Environment keeps all dependencies for the Python project separate from dependencies of other projects. This has a few advantages:
It makes dependency management for the project easy.
It enables using and testing of different library versions by quickly spinning up a new environment and verifying the compatibility of the code with the different version.
调整超参数
在assets下面创建config的内容并且创建yaml文件
配置文件以及HyperParameter-Training Configuration File
mlagents-learn config/moveToGoal.yaml --run-id=TestParameter
基于模型的再训练
mlagents-learn config/moveToGoal.yaml --initialize-from=MoveToGoal --run-id=MoveToGoal2
可视化训练成果
在训练的同时打开另一个cmd
进入同一个虚拟机后输入
tensorboard --logdir results
然后在浏览器中输入
http://localhost:6006/
就可以查看实时的训练结果和目前的效果
后续其他的内容有待补充
网友评论