Unity ML-Agents

The Machine Learning Agents Toolkit is an open source plugin offered for free on GitHub with the aim of providing developers with the possibility of training virtual entities in ad hoc environments using the Unity engine (https://github.com/Unity-Technologies/ml-agents).

For agent training, RL, imitation learning, neuroevolution, and other machine learning methods can be used through an easy to use Python API. Furthermore, TensorFlow-based implementations of algorithms are available to easily train intelligent agents for 2D, 3D, and VR/AR games. The ML-Agents toolkit can be used to develop applications in a very productive way in fact, progress can be evaluated in the rich environments of Unity.

Get Hands-On Reinforcement Learning with R now with O’Reilly online learning.

O’Reilly members experience live online training, plus books, videos, and digital content from 200+ publishers.