Skip to content

Instantly share code, notes, and snippets.

@n0obcoder
Created July 23, 2020 05:59
Show Gist options
  • Save n0obcoder/dd2f2a035bf5f857bdfcd5e120107f37 to your computer and use it in GitHub Desktop.
Save n0obcoder/dd2f2a035bf5f857bdfcd5e120107f37 to your computer and use it in GitHub Desktop.
summary_dir = 'summary'
num_episodes = 500000
display = False # boolean for diplaying/printing the Tic-Tac-Toe board on the terminal. It is suggested to set it to False for training purposes
# exploration-exploitation trade-off factor
epsilon = 0.4 # must be a real number between (0,1)
# learning-rate
alpha = 0.3 # must be a real number between (0,1)
# discount-factor
gamma = 0.95 # must be a real number between (0,1)
playerX_QLearningAgent_name = 'QLearningAgent_X'
player0_QLearningAgent_name = 'QLearningAgent_0'
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment