Using Deep Q-Network to Learn How To Play Flappy Bird

An example also as tutorials for playing Flappy Bird by Deep Q-Network.

Setup

Check installation.md for instructions.

Disclaimer

This work is highly based on the following repos:

1. yenchenlin/DeepLearningFlappyBird: Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
2. sourabhv/FlapPyBird: A Flappy Bird Clone using python-pygame https://sourabhv.github.io/FlapPyBird
3. yanpanlau/Keras-FlappyBird: Using Keras and Deep Q-Network to Play FlappyBird
   • Using Keras and Deep Q-Network to Play FlappyBird
4. nikitasrivatsan/DeepLearningVideoGames: Using Deep Q Networks to Learn Video Game Strategies
5. enhuiz/flappybird-ql: Flappy Bird Q-Learning
   • Improved: w3ntao/q-bird: Flappy Bird with Q-learning https://w3ntao.github.io/q-bird/
6. mldsta/mlds-2018-hw4: HW4 of mlds 2018 Spring

Learning resources

• Reinforcement learning: An introduction: Richard S. Sutton and Andrew G. Barto, MIT Press, Cambridge, MA, 2018.
• ShangtongZhang/reinforcement-learning-an-introduction: Python Implementation of Reinforcement Learning: An Introduction
• flax example: Proximal Policy Optimization
• [RL] Q learning 與 Deep Q Network(DQN)

References

• [1] Mnih Volodymyr, Koray Kavukcuoglu, David Silver, Andrei A. Rusu, Joel Veness, Marc G. Bellemare, Alex Graves, Martin Riedmiller, Andreas K. Fidjeland, Georg Ostrovski, Stig Petersen, Charles Beattie, Amir Sadik, Ioannis Antonoglou, Helen King, Dharshan Kumaran, Daan Wierstra, Shane Legg, and Demis Hassabis. Human-level Control through Deep Reinforcement Learning. Nature, 529-33, 2015.
• [2] Kevin Chen. Deep Reinforcement Learning for Flappy Bird
  • Report
  • Youtube result
• [3] Q Learning: Watkins, C.J.C.H. and Dayan, P. (1992). Q-learning. Machine Learning, 8(3-4), 279-292.
• [4] Andrej Karpathy blog: Deep Reinforcement Learning: Pong from Pixels
  • leonardoaraujosantos's note