Skip to content

Instantly share code, notes, and snippets.

@chuchro3

chuchro3/cartpole

Last active February 24, 2017 21:07
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save chuchro3/3191267c11728237d0d26c032e17a573 to your computer and use it in GitHub Desktop.
Save chuchro3/3191267c11728237d0d26c032e17a573 to your computer and use it in GitHub Desktop.
Download ZIP
CartPole-v1
Raw
cartpole
Tabular Q-Learning on CartPole-v1:
Utilized code from Berkeley's CS188 Q-Learning project
Discretized the state space from continuous values
#cart_x, cart_velocity, pole_theta, pole_velocity
[5,10,20,10]
Introduced an epsilon decay to offer a transition between early exploration and late exploitation
Q-Learning Parameters:
epsilon = 1.0
alpha = .4
gamma = .997
epsilon_decay = .997
alpha_decay = 1.0
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment