Projects

RL Agent for Tron

Light cycles, learned

Role
Personal project
When
Nov 2024 – Feb 2025
Built with
PyTorch, NumPy, Pygame, OpenCV, PPO
  • 74.4%win rate against a random player
  • 41.9%wins against survival strategies (19.3% draws)

I trained a Proximal Policy Optimization agent to play 1v1 Tron competitively, starting with behavior cloning and then curriculum learning against increasingly strong BFS and Voronoi agents.

To measure it I built a 3,000-game evaluation harness. The agent won 74.4% of games against a random player and 41.9% against survival strategies, with 19.3% draws.

NextMars Landmark Classifier