Problem Statement
Program a Tic-Tac-Toe game. Replace the Q-value table with a functional approximation, a neural network.
Running the Code
To get the output, run the following lines.
N = trainTicTacToe(Q);
tictactoe(N)
-
Notifications
You must be signed in to change notification settings - Fork 1
Program a Tic-Tac-Toe game by using Q-learning with a functional approximation, a neural network
License
Ghost1995/Q-Learning-using-Neural-Network
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Program a Tic-Tac-Toe game by using Q-learning with a functional approximation, a neural network
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published