GitHub - ptr-h/reinforcement-learning-racetrack: an implementation of monte carlo, q-learning, sarsa, and dyna-q for an agent in a racetrack environment based on the Sutton and Barto textbook

ptr-h / reinforcement-learning-racetrack Public

an implementation of monte carlo, q-learning, sarsa, and dyna-q for an agent in a racetrack environment based on the Sutton and Barto textbook

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 1 Commit
On-Policy First-Visit Monte Carlo control.ipynb		On-Policy First-Visit Monte Carlo control.ipynb
Q-Learning (Off-Policy TD control).ipynb		Q-Learning (Off-Policy TD control).ipynb
Sarsa (On-Policy TD control).ipynb		Sarsa (On-Policy TD control).ipynb
Tabular Dyna-Q.ipynb		Tabular Dyna-Q.ipynb
racetrack_env.py		racetrack_env.py
track.txt		track.txt