Skip to content

Simple reinforcement learning (Q-Learning) pathfinder for UnicornHatHD.

Notifications You must be signed in to change notification settings

x72y5e/UnicornHatHD_Q_Learning_Path_Finder

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 

Repository files navigation

UnicornHatHD_Q_Learning_Path_Finder

Simple reinforcement learning (Q-Learning) pathfinder for UnicornHatHD.

This programme requires the unicornhathd module for the raspberry pi.

Run the programme by invoking the play() command. Specify verbose=1 to see information on rewards, and epsilon (exploration criteria).

Additional obstacles / mazes etc can be added by amending the build_walls function.

Those familiar with Q-Learning may wish to alter the initial epsilon / epsilon decay values.

About

Simple reinforcement learning (Q-Learning) pathfinder for UnicornHatHD.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages