/SonicTheHedgehog2-ReinforcmentLearning

This project implements an agent for playing the SonicTheHedgehog2 game from a ROM file using the Proximal Policy Optimization (PPO) algorithm from the stablebaselines3 library. The agent is trained to learn the optimal actions to take at each step in the game in order to complete the level and maximize the score.

Primary LanguageJupyter Notebook

No issues in this repository yet.