1
$\begingroup$

I am creating a neural network to play tic tac toe. I have it play 1000 random games to gather the training data and append the winning data into a list of the board before the move as the X value and the move as the Y value. I am training the data with this line:

model.fit({'input': x}, {'targets': y}, n_epoch=50, snapshot_step=500, show_metric=True, run_id='openai_learning')

And the model that I am using is this:

network = input_data(shape=(None, 9), name='input')

network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.8)

network = fully_connected(network, 256, activation='relu')
network = dropout(network, 0.8)

network = fully_connected(network, 512, activation='relu')
network = dropout(network, 0.8)

network = fully_connected(network, 256, activation='relu')
network = dropout(network, 0.8)

network = fully_connected(network, 128, activation='relu')
network = dropout(network, 0.8)

network = fully_connected(network, 1, activation='linear')
network = regression(network, optimizer='adam', learning_rate=0.01, loss='mean_square', name='targets')

model = tflearn.DNN(network, tensorboard_dir='log')

But when I go to predict the next move it keeps on predicting to play the piece on the board where there is another piece. What would be the best way to prevent it? The only things that I can think of is finding the closest open piece on the board or tweak the parameters of training.

Here is the source file for the game:

https://raw.githubusercontent.com/ben60501/special-potato/master/TicTacToe.py

$\endgroup$
0
1
$\begingroup$

I have created neural networks to play tic-tac-toe before. Instead of having just 1 output, you should have 9 outputs. Each output representing the probability that one of the 9 squares on the board is a good move. This turns the game more into a classification problem.

Example (playing as O):

Given board:

X - X
O - O
X - -

The output could be:

0.1 0.5 0.2
0.7 0.6 0.1
0.3 0.4 0.4

Filter out the taken spots:

- 0.5 - 
- 0.6 - 
- 0.4 0.4

So your next move is the spot with p=0.6!

This is far better than chosing a random near spot when the outputted spot is already taken. While training, you have to make outputs look like this:

0 0 0 
0 1 0 
0 0 0 

So there must only be one 1 in the output array!

$\endgroup$
2
  • $\begingroup$ So your next move is the spot with p=0.6! Surely this can't be a probability. The total in the filtered board is $1.9 > 1$. $\endgroup$
    – Sycorax
    May 2 '17 at 21:54
  • $\begingroup$ I might have used the term "probability" different than youre used to. 0,6 means that there is a 60% probability that that move is a good move, that doesnt mean that any of the other moves cant be a good move as well! $\endgroup$ May 2 '17 at 21:56

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.