Unity has jumped into the world of machine learning solutions with their open beta release of the Unity Machine Learning Agents SDK (ML-Agents SDK).
Released on Github, the SDK brings machine learning to games, allowing researchers and developers to create intelligent agents that can be trained using reinforcement learning, neuroevolution, or other machine learning methods through a Python API.
- Integration with Unity Engine
- Multiple cameras
- Flexible Multi-agent support
- Discrete and continuous action spaces
- Python 2 and 3 control interface
- Visualizing network outputs in the environment
- Tensorflow Sharp Agent Embedding (Experimental)
Learn more about these features and more at the Unity blog announcement.