Skip to content

DavidMachineLearning/CartPole_RL

Repository files navigation

CartPole_RL

A detailed description can be found Here.

Game description:

A pole is attached by an un-actuated joint to a cart, which moves along a frictionless track. The system is controlled by applying a force of +1 or -1 to the cart. The pendulum starts upright, and the goal is to prevent it from falling over. A reward of +1 is provided for every time-step that the pole remains upright. The episode ends when the pole is more than 15 degrees from vertical, or the cart moves more than 2.4 units from the center.

Files:

  • CartPole.ipybn Jupyter notebook with entire process
  • KerasDQN.py Python file containing an easy to use structure (keras version)
  • TFDQN.py Python file containing an easy to use structure (Tensorflow version)
  • cartpole.mp4 mp4 video of the trained model
  • cartpole.mkv mkv video of the trained model

About

Appling DQN to the cart pole game

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors