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

文件历史

Vilmantas Balasevicius 5d3141d7 Implemented ArticulatedCrawler agent reset via crawler body prefab respawn. Reimplemented ArticulatedCrawlerDynamicTarget scene and associated prefabs. Modified camera follow script to track respawned articulated body object - still need to generalize.		5 年前
..
Assets	Implemented ArticulatedCrawler agent reset via crawler body prefab respawn. Reimplemented ArticulatedCrawlerDynamicTarget scene and associated prefabs. Modified camera follow script to track respawned articulated body object - still need to generalize.	5 年前
ProjectSettings	Somewhat working Articulated Reacher, however still WIP: training performance is way different from standard RB version.	5 年前
README.md	Update readmes to be more informative (#1194)	6 年前
UnitySDK.sln.DotSettings	[coding conventions] Revert NNModelImporter rename and remove NonAlloc Collider check suggestion from rider. (#2571)	5 年前

README.md

Unity ML-Agents SDK

Contains the ML-Agents Unity Project, including both the core plugin (in Scripts), as well as a set of example environments (in Examples).