brunobelluomini/flappy_bird_with_TD_learning
Teaching a machine how to play Flappy Bird using Sarsa, Q-Learning (ε-greedy policy) and Expected Sarsa (ε-greedy policy)
Jupyter NotebookMIT
Stargazers
No one’s star this repository yet.
Teaching a machine how to play Flappy Bird using Sarsa, Q-Learning (ε-greedy policy) and Expected Sarsa (ε-greedy policy)
Jupyter NotebookMIT
No one’s star this repository yet.