yenchenlin / DeepLearningFlappyBird

Flappy Bird hack using Deep Reinforcement Learning (Deep Q-learning).

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

how to start training ...

SeekPoint opened this issue · comments

how to start training ...
commented

I want to know too, please help me

From the README.md:

How to reproduce?

Comment out these lines

Modify deep_q_network.py's parameter as follow:

OBSERVE = 10000
EXPLORE = 3000000
FINAL_EPSILON = 0.0001
INITIAL_EPSILON = 0.1

Thanks @tnarik ;)

please,what time need in cpu?

Reagan Enoch