You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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.
In this project, I created an agent to solve the CartPole task using the stablebaselines3 library. CartPole is a problem from the OpenAI Gym catalog, in which the goal is to maintain balance of a wooden pole using motors attached to its ends. The agent must decide whether to move the pole left or right to maintain balance.
Nokia's classic 'snake' game, written in NumPy and converted into a Gymnasium Environment() for use with gradient-based reinforcement learning algorithms
This project implements an agent for playing the VizDoom game on various levels 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.