Inspiration
We were inspired by the legendary success of AlphaGo and how self-play training creates exponentially improving AI. We wanted to apply that same paradigm to the Case Closed challenge - building an AI that doesn't just play well, but gets better by competing against itself. The Tron-inspired grid battle setup was perfect for this: every game generates training data, and every cycle produces a stronger agent.
Built With
- https://github.com/likithkancharlapalli/case-closed-agent
Log in or sign up for Devpost to join the conversation.