Skip to content
This repository has been archived by the owner on Jan 8, 2024. It is now read-only.

Latest commit

 

History

History
12 lines (7 loc) · 595 Bytes

README.md

File metadata and controls

12 lines (7 loc) · 595 Bytes

310-Final-Project

This is an extension of Unity Technology's ML Dodgeball tutorial, found here https://github.com/Unity-Technologies/ml-agents-dodgeball-env.

Our additions:

Agents are now reinforced positively for throwing dodgeballs and are negatively reinforced for falling into lava.

Environmentally, purple team now starts on a raised castle-like structure and a lava moat with a bridge divides the playing field.

Additionally, moving cover and platforms have been added in an attempt to see if agents take advantage of the routes and strategic cover opened up by by these platforms.