search

yenchenlin / DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).
MIT License
6.65k stars 2.04k forks source link

Further improvement #9

Open yenchenlin opened 8 years ago

yenchenlin commented 8 years ago

Below are some resources which may improve current implementation

  1. Algorithm suggested here
  2. Prioritized Experience Replay

I will try to implement all these when I got time!