Skip to content

Applying Markov Decision Processes and Q-Learning to a robot movement model

Notifications You must be signed in to change notification settings

vlfom/StepLearn

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 
 
 
 
 

Repository files navigation

StepLearn

A Machine Learning project on applying Markov decision processes and Q-Learning on robot movement model.

The idea is to apply Q-Learning technique to a two-legged robot, whose goal is to move forward (rightwards) as fast as possible. The program allows you to change robot's legs' size and position of knees; then you can start monitoring its learning process.

Some examples of robot's movement after learning stage:

About

Applying Markov Decision Processes and Q-Learning to a robot movement model

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages