Machine Learning Applications for FrameIT
In the FrameIT project (#1), we use the Unity game engine in combination with MMT to have access to mathematical knowledge management techniques and interact with the knowledge in the game world.
Building on the Unity machine learning integration, we would like to teach an agent to play the games developed with the FrameIT method. Possible approaches may be:
- reinforcement learning via reward function
- imitation learning
- modularizing tasks based on the MMT knowledge formalization