A flappy bird game that learns to play by itself using Deep Q Learning and JavaScript and exciting technologies such as Tensorflow.js, D3 and Webpack.
You can click here for live demo.
This project follows the description of the Deep Q Learning algorithm described in Playing Atari with Deep Reinforcement Learning and shows that this learning algorithm can be further generalized to the notorious Flappy Bird.
Moreover, in order to optimize it even more, I used DDQN architecture.
Clone and install dependecies
git clone https://github.com/danielpaz6/Flappy-Birds-DQN.git
cd Flappy-Birds-DQN
npm install
npx webpack