https://github.com/ardamavi/Game-Bot

Artificial intelligence learn playing any game with watching you.
https://github.com/ardamavi/Game-Bot

artificial-intelligence deep-learning keras tensorflow

Last synced: 2 months ago
JSON representation

Artificial intelligence learn playing any game with watching you.

• Host: GitHub
• URL: https://github.com/ardamavi/Game-Bot
• Owner: ardamavi
• License: apache-2.0
• Created: 2017-06-23T12:14:22.000Z (almost 7 years ago)
• Default Branch: master
• Last Pushed: 2023-05-27T19:53:45.000Z (about 1 year ago)
• Last Synced: 2024-01-21T23:46:57.020Z (5 months ago)
• Topics: artificial-intelligence, deep-learning, keras, tensorflow
• Language: Python
• Homepage:
• Size: 23.4 KB
• Stars: 382
• Watchers: 26
• Forks: 95
• Open Issues: 24
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Lists

• awesome - ardamavi/Game-Bot - Artificial intelligence learn playing any game with watching you. (Python)

README

        
# Game Bot

### By Arda Mavi

Artificial intelligence that learns to play any game by watching you.

## How does this work?

- First: Run program and play any game for a little bit.

- Second: Run program and watch the artificial intelligence play the game.

## How does it work behind the scenes?

When you run the training program, the program listens for your keyboard and mouse moving, then it saves those movements.


Artificial intelligence learn: When I push any button?


And when you run the program, it plays the game just like you!

## But how does it learn?

##### Magic! (just joking)

With deep learning.


Deep Learning is a subfield of machine learning with neural networks inspired by the structure of the brains artificial neural networks.

### Playing with Artificial Intelligence:

1. Open your desired game (If you have already trained the artificial intelligence).

2. Run `python3 ai.py` command in terminal.

### Creating Training Dataset:

1. Run `python3 create_dataset.py` command in terminal.

2. Play your desired game.

3. Stop `create_dataset` program with `Cntrl-C` in terminal.

### Model Training:

`python3 train.py`

### Using TensorBoard:

`tensorboard --logdir=Data/Checkpoints/logs`

### Important Notes:

- Tested in Python version 3.6.0

- Install necessary modules with `sudo pip3 install -r requirements.txt` command.

## WINDOWS Installation:

- Install Python 3.6.0 : https://www.python.org/downloads/release/python-360/

- Run CMD and Input Command `pip3 install -r requirements.txt`

### This project is still being worked on ...