An AI TicTacToe Qagent trained with reinforced learning. To make a move use the following numbers as board locations,
7 | 8 | 9
4 | 5 | 6
1 | 2 | 3
When you resresh the page, the game start again.
Values of each action of the AI given your move. A action which is not allowed is set to -1000.
0.0 | 0.0 | 0.0 |
0.0 | 0.0 | 0.0 |
0.0 | 0.0 | 0.0 |