Basic implementation of q-learning in a 4*4 grid.
Agent starts at (0,0).
White cells have a negative reward.
Episode ends when agent finds the black cell (positive reward).
-
Notifications
You must be signed in to change notification settings - Fork 0
ineeve/q-learning
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
A Q-Learning Implementation
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published