-
An algorithm that plays tic tac toe (naughts and crosses) optimally against a human using the negamax implementation of minimax. See: https://en.wikipedia.org/wiki/Negamax
-
An algorithm that learns to play tic tac toe (naughts and crosses) by playing against itself using Q-learning. See: https://en.wikipedia.org/wiki/Q-learning
lsx0519 / tictactoe Goto Github PK
View Code? Open in Web Editor NEWThis project forked from rpreen/tictactoe
Q-learning and negamax algorithms to play tic tac toe (naughts and crosses.)
License: GNU General Public License v3.0