Unity 机器学习代理工具包 (ML-Agents) 是一个开源项目,它使游戏和模拟能够作为训练智能代理的环境。
您最多选择25个主题 主题必须以中文或者字母或数字开头,可以包含连字符 (-),并且长度不得超过35个字符
 
 
 
 
 

1.2 KiB

Unity Inference Engine

The ML-Agents toolkit allows you to use pre-trained neural network models inside your Unity games. This support is possible thanks to the Unity Inference Engine. The Unity Inference Engine is using compute shaders to run the neural network within Unity.

Supported devices

Scripting Backends : The Unity Inference Engine is generally faster with IL2CPP than with Mono for Standalone builds. The Unity Inference Engine supposedly works on any Unity supported platform but we only tested for the following platforms :

  • Linux 64 bits
  • Mac OS X 64 bits (OpenGLCore Graphics API is not supported)
  • Windows 64 bits
  • iOS
  • Android

Using the Unity Inference Engine

When using a Learning Brain, drag the .nn file into the Model field in the Inspector. Uncheck the Control checkbox for the corresponding Brain in the BroadcastHub of the Academy. Select the Inference Device : CPU or GPU you want to use for Inference.

Note: For most of the models generated with the ML-Agents toolkit, CPU will be faster than GPU. Only use GPU if you have a large number of agents using visual observations.