This project is for implementing Q-learning and SARSA algorithms for the Snake-And-Apple game. The code will first learn Q-table then try its best to get the apple. We can't play the full game with these two algorithms. So, we just reach the first apple that appears on the map. Something like solving the maze. To do the full game, we need to do it with Deep Q-Learning.
forked from aqeelanwar/Snake-And-Apple
-
Notifications
You must be signed in to change notification settings - Fork 0
Reinforcement learning implementation using the game snake and apple based on Q-learning, SARSA, and simple Deep Q-learning algorithms
License
armanbarghi/Snake-And-Apple
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Reinforcement learning implementation using the game snake and apple based on Q-learning, SARSA, and simple Deep Q-learning algorithms
Topics
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published
Languages
- Jupyter Notebook 100.0%