Created
October 16, 2022 06:14
-
-
Save SolClover/c41ed762389ed609fe4748db09dd0a4c to your computer and use it in GitHub Desktop.
This file contains 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
# SARSA parameters | |
alpha = 0.1 # learning rate | |
gamma = 0.95 # discount factor | |
# Training parameters | |
n_episodes = 100000 # number of episodes to use for training | |
n_max_steps = 100 # maximum number of steps per episode | |
# Exploration / Exploitation parameters | |
start_epsilon = 1.0 # start training by selecting purely random actions | |
min_epsilon = 0.0 # the lowest epsilon allowed to decay to | |
decay_rate = 0.00001 # epsilon will gradually decay so we do less exploring and more exploiting as Q-function improves |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment