yenchenlin / DeepLearningFlappyBird

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

Why parameters from codes and those of the paper are quite different?what is better? #22

Closed baimin1 closed 7 years ago

baimin1 commented 7 years ago

Why parameters (and network struct) from codes and those of the paper are quite different?what is better? Thank you

boolings are all commented, why ? Such as

h_pool2 = max_pool_2x2(h_conv2)

yenchenlin commented 7 years ago

Hello, I will update the code recently! However, current code did not accurately follow the DQN paper, so I did it only because it work.