Alternatives To Deeplearningflappybird
Project NameStarsDownloadsRepos Using ThisPackages Using ThisMost Recent CommitTotal ReleasesLatest ReleaseOpen IssuesLicenseLanguage
Pytorch64,66914614 hours ago23August 10, 202211,516otherC++
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Tensorflow Examples42,312
5 months ago218otherJupyter Notebook
TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)
Pytorch Tutorial25,860
22 days ago88mitPython
PyTorch Tutorial for Deep Learning Researchers
Awesome Deep Learning Papers21,874
3 years ago34TeX
The most cited deep learning papers
Ml From Scratch21,618
5 months ago4June 17, 201748mitPython
Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.
Awesome Tensorflow16,809
3 months ago30cc0-1.0
TensorFlow - A curated list of dedicated resources
5 months ago13apache-2.0Lua
Face recognition with deep neural networks.
3 years ago22
Papers with code. Sorted by stars. Updated weekly.
a year ago53HTML吴恩达老师的深度学习课程笔记及资源)
Neural Networks And Deep Learning14,073
a month ago8Python
Code samples for my book "Neural Networks and Deep Learning"
Alternatives To Deeplearningflappybird
Select To Compare

Alternative Project Comparisons

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

7 mins version: DQN for flappy bird


This project follows the description of the Deep Q Learning algorithm described in Playing Atari with Deep Reinforcement Learning [2] and shows that this learning algorithm can be further generalized to the notorious Flappy Bird.

Installation Dependencies:

  • Python 2.7 or 3
  • TensorFlow 0.7
  • pygame
  • OpenCV-Python

How to Run?

git clone
cd DeepLearningFlappyBird

What is Deep Q-Network?

It is a convolutional neural network, trained with a variant of Q-learning, whose input is raw pixels and whose output is a value function estimating future rewards.

For those who are interested in deep reinforcement learning, I highly recommend to read the following post:

Demystifying Deep Reinforcement Learning

Deep Q-Network Algorithm

The pseudo-code for the Deep Q Learning algorithm, as given in [1], can be found below:

Initialize replay memory D to size N
Initialize action-value function Q with random weights
for episode = 1, M do
    Initialize state s_1
    for t = 1, T do
        With probability ϵ select random action a_t
        otherwise select a_t=max_a  Q(s_t,a; θ_i)
        Execute action a_t in emulator and observe r_t and s_(t+1)
        Store transition (s_t,a_t,r_t,s_(t+1)) in D
        Sample a minibatch of transitions (s_j,a_j,r_j,s_(j+1)) from D
        Set y_j:=
            r_j for terminal s_(j+1)
            r_j+γ*max_(a^' )  Q(s_(j+1),a'; θ_i) for non-terminal s_(j+1)
        Perform a gradient step on (y_j-Q(s_j,a_j; θ_i))^2 with respect to θ
    end for
end for



Since deep Q-network is trained on the raw pixel values observed from the game screen at each time step, [3] finds that remove the background appeared in the original game can make it converge faster. This process can be visualized as the following figure:

Network Architecture

According to [1], I first preprocessed the game screens with following steps:

  1. Convert image to grayscale
  2. Resize image to 80x80
  3. Stack last 4 frames to produce an 80x80x4 input array for network

The architecture of the network is shown in the figure below. The first layer convolves the input image with an 8x8x4x32 kernel at a stride size of 4. The output is then put through a 2x2 max pooling layer. The second layer convolves with a 4x4x32x64 kernel at a stride of 2. We then max pool again. The third layer convolves with a 3x3x64x64 kernel at a stride of 1. We then max pool one more time. The last hidden layer consists of 256 fully connected ReLU nodes.

The final output layer has the same dimensionality as the number of valid actions which can be performed in the game, where the 0th index always corresponds to doing nothing. The values at this output layer represent the Q function given the input state for each valid action. At each time step, the network performs whichever action corresponds to the highest Q value using a ϵ greedy policy.


At first, I initialize all weight matrices randomly using a normal distribution with a standard deviation of 0.01, then set the replay memory with a max size of 500,00 experiences.

I start training by choosing actions uniformly at random for the first 10,000 time steps, without updating the network weights. This allows the system to populate the replay memory before training begins.

Note that unlike [1], which initialize ϵ = 1, I linearly anneal ϵ from 0.1 to 0.0001 over the course of the next 3000,000 frames. The reason why I set it this way is that agent can choose an action every 0.03s (FPS=30) in our game, high ϵ will make it flap too much and thus keeps itself at the top of the game screen and finally bump the pipe in a clumsy way. This condition will make Q function converge relatively slow since it only start to look other conditions when ϵ is low. However, in other games, initialize ϵ to 1 is more reasonable.

During training time, at each time step, the network samples minibatches of size 32 from the replay memory to train on, and performs a gradient step on the loss function described above using the Adam optimization algorithm with a learning rate of 0.000001. After annealing finishes, the network continues to train indefinitely, with ϵ fixed at 0.001.


Checkpoint not found

Change first line of saved_networks/checkpoint to

model_checkpoint_path: "saved_networks/bird-dqn-2920000"

How to reproduce?

  1. Comment out these lines

  2. Modify's parameter as follow:

OBSERVE = 10000
EXPLORE = 3000000


[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] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing Atari with Deep Reinforcement Learning. NIPS, Deep Learning workshop

[3] Kevin Chen. Deep Reinforcement Learning for Flappy Bird Report | Youtube result


This work is highly based on the following repos:

  1. [sourabhv/FlapPyBird] (sourabhv/FlapPyBird)
  2. asrivat1/DeepLearningVideoGames
  3. yenchenlin1994/DeepLearningFlappyBird
Popular Deep Learning Projects
Popular Network Projects
Popular Machine Learning Categories
Related Searches

Get A Weekly Email With Trending Projects For These Categories
No Spam. Unsubscribe easily at any time.
Reinforcement Learning
Flappy Bird