flming / dqn_flappy_bird

Using deep Q-networks to train an agent to play flappy bird.

Deep Q-networks for flappy bird

Roadmap

• Implement 2013 NIPS paper's DQN(with replay buffer)
• Implement 2015 Nature paper's DQN(add the target network)
• Implement double DQN
• Implement Dueling DQN

Results

Each approach both played about 500k frame in my computer.

approach	mean score	highest score
2013NIPS	20.534	468
2015Nature	25.121	931
double_DQN	31.530	870
dueling_DQN	30.520	797

The score here cannot strictly represent the pros and cons of the algorithm.

You can download the trained model and logs

The change of mean Q value:

The change of score:

Requirements

• tensorflow
• pygame
• opencv

pip install tensorflow pygame opencv-python

How to run

git clone https://github.com/FLming/DQN_flappy_bird.git
cd DQN_flappybird
python flappybird.py

change the approach just change the code in flappybird.py e.g.

from double_DQN import DeepQNetworks 
from DQN_Nature import DeepQNetworks

if you wanna see network architecture, the change of variables and scores.

tensorboard --logdir logs

if you wanna speed traning up, comment FPSCLOCK.tick(FPS) in wrapped_flappy_bird.py or add FPS

Reference

• repo: floodsung/DRL-FlappyBird
• repo: openai/baselines/deepq
• repo: MorvanZhou/Reinforcement-learning-with-tensorflow