Tic-Tac-Toe-Machine-Leaning-Using-Reinforcement-Learning

A Python Program to implement Machine Learning for the Game Tic Tac Toe (3x3) using Reinforcement Learning (Q learning technique) and tensorflow.

Tested on windows and ubutnu with Python 3.5.2 (packages numpy, tensorflow and flask are required)

To train the model, Run the below command:

python deep_reinforcement_learning.py

Note: if its not the first time that your training the model you might want to change e = epsilon to e = 0 on line 214

To Play the game with Ticky, Run the below command:

python server.py

Note: you might want to change the server port address on line 61 if needed.