Last active
February 24, 2017 21:07
-
-
Save chuchro3/3191267c11728237d0d26c032e17a573 to your computer and use it in GitHub Desktop.
CartPole-v1
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
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