This project features a reinforcement learning agent that learns from experience in order to keep a pole inside a virtual environment steady, improving over time the amount of time it keeps it without falling.
For the environment this project uses OpenAI’s gym CartPole game. In this game a pole is attached by an un-actuated joint to a cart, which moves along a frictionless track. The pendulum starts upright, and the goal is to prevent it from falling over by increasing and reducing the cart's speed.