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。

unity3d unity unity-tech reinforcement-le deep-learning deep-reinforcement-learning neural-networks

目录树: 083777ca

文件历史

GitHub a2c8b4c4 Make GridSensor a non allocating object after initialization. (#5014 ) Co-authored-by: Chris Elion <chris.elion@unity3d.com>		3 年前
..
Assets	Add an example project for the InputSystemActuator. (#4976)	3 年前
Packages	Make GridSensor a non allocating object after initialization. (#5014)	3 年前
ProjectSettings	Add an example project for the InputSystemActuator. (#4976)	3 年前
.gitignore	Add an example project for the InputSystemActuator. (#4976) (#4980)	3 年前
README.md	Add an example project for the InputSystemActuator. (#4976) (#4980)	3 年前

README.md

ML-Agents Input System Package Example

Overview

This small example project shows how to integrate games that use the input system package with ML-Agents. This modified PushBlock scene has a PlayerController script which handles all of the input to control the cube. On it is an InputActuatorComponent which takes the actions associated with the gameObject from the PlayInput component and enables the simulation of input data in order to train and run inference with ml-agents.

README.md

ML-Agents Input System Package Example

Overview

See Also