參考內(nèi)容
CodeMonkey - How to use Machine Learning AI in Unity! (ML-Agents)
Making a New Learning Environment
Unity官方Github地址和文檔內(nèi)容
Unity ML-Agents Toolkit Documentation
CodeMonkey 更多的關(guān)于UnityML的系列內(nèi)容
Machine Learning AI in Unity (ML-Agents)
常見問題
安裝python https://www.python.org/downloads/windows/
如果你的命令行輸入不起作用氏豌？windows下命令行模式中cd命令無效的原因
關(guān)于pytorch是什么？
pytorch與tensorflow https://zhuanlan.zhihu.com/p/104842311
適合PyTorch小白的官網(wǎng)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/
如何最簡單馁启、通俗地理解Pytorch朴上？ https://www.zhihu.com/question/439496333/answer/1715174511
你可以把 pytorch 理解為一個(gè)支持 gpu 的鹦筹，可以進(jìn)行求導(dǎo)的計(jì)算器中姜。新添的這兩個(gè)功能現(xiàn)在主要是給神經(jīng)網(wǎng)絡(luò)用的椭符，所以 pytorch 里面也加了很多神經(jīng)網(wǎng)絡(luò)用的輔助工具
為什么需要安裝Python虛擬機(jī)？
py的虛擬環(huán)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.
調(diào)整超參數(shù)
在assets下面創(chuàng)建config的內(nèi)容并且創(chuàng)建yaml文件
配置文件以及HyperParameter-Training Configuration File
mlagents-learn config/moveToGoal.yaml --run-id=TestParameter
基于模型的再訓(xùn)練
mlagents-learn config/moveToGoal.yaml --initialize-from=MoveToGoal --run-id=MoveToGoal2
可視化訓(xùn)練成果
在訓(xùn)練的同時(shí)打開另一個(gè)cmd
進(jìn)入同一個(gè)虛擬機(jī)后輸入
tensorboard --logdir results
然后在瀏覽器中輸入
http://localhost:6006/
就可以查看實(shí)時(shí)的訓(xùn)練結(jié)果和目前的效果
后續(xù)其他的內(nèi)容有待補(bǔ)充
