Python 3.6 implementation of how to build and apply the Q-Learning algorithm with E-greedy approach to escape from a 2D maze with static fire and obstacles. All this can be extrapolated to several cases in which the environment could be represented as a grid of strings with spatial sense, such as mazes, etc.
-
Notifications
You must be signed in to change notification settings - Fork 0
Q-learning pathscaping application implemented without any ML library
GuzmanGP/Q-Learning-maze-construction-E-greedy-approach-
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Q-learning pathscaping application implemented without any ML library
Topics
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published