Skip to content

Abezzam10/CartPole_problem

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

CartPole_problem

CartPole problem with reinforcement learning.

A novel way to approach the Cartpole problem rather than using the random moves using Open AI Gym Lib. Instead of taking random moves along the x-axis which causes a shorter run time of the problem(max of 15 secs), I introduce a set of parameters to run this for greater amounts of time.

Moving right to left is decided by a set of parameters in my case and runs 10,000 (100 sets of games) without rendering. Limit of 200 moves are accomplished in this process and significantly outperforms the random approach of decsison making.

Description

About

CartPole problem with reinforcement learning. 10,000 parallel games without rendering

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages