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 aims to implement a reinfrcement learning agent using Proximal Policy Optimization (PPO). And given the Unity environment of the "Karting Microgame", it can be used to train a robust agent on multiple tracks which can compete against other implementations.
Reinforcement Learning with Stable Baselines3: Train and evaluate a CartPole agent using Stable Baselines3 library. Includes code for training, saving, and testing the model, along with a GIF visualization of the trained agent.
Reinforcement learning project for training an agent to play Atari Breakout, using algorithms like Multiple Tile Coding, Radial Basis Functions, and REINFORCE. Code, insights, and performance analysis provided.