Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/matousss/ttt_ai
TicTacToe with neural network
https://github.com/matousss/ttt_ai
keras neural-network python tictactoe
Last synced: about 1 month ago
JSON representation
TicTacToe with neural network
- Host: GitHub
- URL: https://github.com/matousss/ttt_ai
- Owner: matousss
- Created: 2022-04-18T21:02:42.000Z (almost 3 years ago)
- Default Branch: master
- Last Pushed: 2022-12-15T21:59:48.000Z (about 2 years ago)
- Last Synced: 2024-11-07T16:28:53.098Z (3 months ago)
- Topics: keras, neural-network, python, tictactoe
- Language: Python
- Homepage:
- Size: 192 KB
- Stars: 0
- Watchers: 1
- Forks: 1
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# TicTacToe AI
This project implements basic game of TicTacToe with size 3x3. Current version offers 3 opponent types: Human, MiniMax and AI.
## Players
| Name | Move is determined by | Opponent |Trainable* |
|---------|------------------------------------|----------|------------
| Human | clicking on field with mouse | 🗸 | ⨉ |
| Random | pseudorandom number genrator | ⨉ | 🗸 |
| MiniMax | MiniMax algorithm | 🗸 | 🗸 |
| AI | neural network | 🗸 | 🗸 |
\*Type can be used to train model.
## `model_maker.py`
In order to use "AI Player" you have to create and train a model. To simplify this action project contains `model_maker.py` script, which provides basic GUI to generate data, create and train model. It cam be also used to train existing model.
- Generate data - generate and add data to memory
- Dump data - Removes data from memory
- Train current model - Trains `model.h5` with data from memory
- Train new model - Creates new `model.h5` or overwrites current
## `main.py`
In order to run the game you have to create model or import model. Then run script `main.py`.
You will see following window:
After running all games or closing game, window with score is shown.
