A Q Learning algorithm where the agent learns to go from 1x1 square to the goal without touching the red obstacle squares in a nxn grid. It perfects its learning on around 140-150 generations.
-
Notifications
You must be signed in to change notification settings - Fork 0
License
burcukilic/Q-learning-maze-solver
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published