0
$\begingroup$

I'm currently implementing tabular q-learning for 3x3 tictactoe in python and I'm new to RL and still have a hard time to understand RL. Therefore, I would like to know one thing:

  1. In (tabular) q-learning for tictactoe 3x3 I would like to know in which order the q-value would be added to the state and action pair when I there is only a single episode? Would it be the empty state first or last?:
"('_________', 8)": ?,
"('_____O__X', 3)": ?,
"('___X_OO_X', 0)": ?,
"('X__X_OOOX', 1)": ?,
"('XX_XOOOOX', 2)": ?,
Improve this question
$\endgroup$
1
  • 1
    $\begingroup$ Welcome to our community. Can you please reformulate the title as a question and precisely as specific question? Thanks $\endgroup$
    – nbro
    Commented Jan 31 at 13:05

0

Reset to default

You must log in to answer this question.

Browse other questions tagged .