https://github.com/flakas/bubble-shooter-bot

Tensorflow and Q-Learning based Python bot for the Bubble Shooter flash game
https://github.com/flakas/bubble-shooter-bot

bot bubble-shooter keras opencv python q-learning reinforcement-learning tensorflow

Last synced: 21 days ago
JSON representation

Tensorflow and Q-Learning based Python bot for the Bubble Shooter flash game

• Host: GitHub
• URL: https://github.com/flakas/bubble-shooter-bot
• Owner: flakas
• Created: 2019-08-05T21:37:29.000Z (over 5 years ago)
• Default Branch: master
• Last Pushed: 2022-11-22T02:40:06.000Z (over 2 years ago)
• Last Synced: 2025-03-24T12:56:16.994Z (about 1 month ago)
• Topics: bot, bubble-shooter, keras, opencv, python, q-learning, reinforcement-learning, tensorflow
• Language: Python
• Homepage:
• Size: 61.5 KB
• Stars: 5
• Watchers: 1
• Forks: 1
• Open Issues: 5
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
Q-Learning Bubble Shooter bot

=============================

Bubble Shooter game: [https://www.kongregate.com/games/Paulussss/bubbles-shooter](https://www.kongregate.com/games/Paulussss/bubbles-shooter)

Demo gameplay:

[![Basic Puzlogic game bot with OpenCV and Python](https://img.youtube.com/vi/9K343IWO2N4/0.jpg)](https://www.youtube.com/watch?v=9K343IWO2N4)

A blog post writeup on how and why the bot was built: [Q-learning bot for Bubble Shooter](https://tautvidas.com/blog/2019/08/q-learning-bot-for-bubble-shooter/)

Requires:

- `geckodriver` in your `$PATH`

- `OpenCV` installed on the system

```

virtualenv -p python3 --system-site-packages venv

source venv/bin/activate

pip install -r requirements.txt

cd webpage && sudo python -m SimpleHTTPServer 80 & # to run a local version of Bubble Shooter

python train.py

python demo.py

```