• Stars
    star
    576
  • Rank 77,502 (Top 2 %)
  • Language
    Python
  • Created over 8 years ago
  • Updated about 4 years ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN using Tensorflow)

Playing Flappy Bird Using Deep Reinforcement Learning (Based on Deep Q Learning DQN)

Include NIPS 2013 version and Nature Version DQN

I rewrite the code from another repo and make it much simpler and easier to understand Deep Q Network Algorithm from DeepMind

The code of DQN is only 160 lines long.

To run the code, just type python FlappyBirdDQN.py

Since the DQN code is a unique class, you can use it to play other games.

About the code

As a reinforcement learning problem, we knows we need to obtain observations and output actions, and the 'brain' do the processing work.

Therefore, you can easily understand the BrainDQN.py code. There are three interfaces:

  1. getInitState() for initialization
  2. getAction()
  3. setPerception(nextObservation,action,reward,terminal)

the game interface just need to be able to feed the action to the game and output observation,reward,terminal

Disclaimer

This work is based on the repo: yenchenlin1994/DeepLearningFlappyBird

More Repositories

1

Deep-Learning-Papers-Reading-Roadmap

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!
Python
37,895
star
2

Meta-Learning-Papers

Meta Learning / Learning to Learn / One Shot Learning / Few Shot Learning
2,612
star
3

LearningToCompare_FSL

PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)
Python
1,043
star
4

DDPG

Reimplementation of DDPG(Continuous Control with Deep Reinforcement Learning) based on OpenAI Gym + Tensorflow
Python
549
star
5

Deep-Reasoning-Papers

Recent Papers including Neural Symbolic Reasoning, Logical Reasoning, Visual Reasoning, planning and any other topics connecting deep learning and reasoning
295
star
6

LLM-with-RL-papers

A collection of LLM with RL papers
208
star
7

wechat_jump_end_to_end

Playing Wechat Jump Game with End-to-End Convolutional Neural Networks
Python
180
star
8

DQN-Atari-Tensorflow

Simplest Version of playing Atari with Deep Q Learning in Tensorflow
Python
160
star
9

Lifelong-Learning-Paper-List

Lifelong/Continual Learning Paper List
150
star
10

Tracking-on-iOS

Test Several Visual Object Tracking Algorithm including CMT,TLD,CT on iOS
C++
73
star
11

a2c_cartpole_pytorch

advantage actor-critic reinforcement learning for openai gym cartpole
Python
64
star
12

PlaneWar

Written in Swift Using latest Sprite kit a copy version of wechat game 微信打飞机!
Swift
62
star
13

meta-critic-networks

Pytorch code for Arxiv Paper: Learning to learn: Meta-Critic Networks for Sample-Efficient Learning
Python
56
star
14

wechat_jump_end_to_end_train

Playing Wechat Jump Game with End-to-End Convolutional Neural Networks (Train code)
Python
45
star
15

DDPG-tensorflow

DDPG on OpenAI Gym Pendulum
Python
19
star
16

CLDrone

Autonomous Quadrotor Simulation Research Platform based on ROS,Gazebo,Pixhawk,DRCsim..
C++
14
star
17

PhysicsFieldsWorld

Swift
14
star
18

researchGPT

a collection of cookbooks to use ChatGPT for academic research.
Python
8
star
19

iOS_WiFi_EV3_Library

Objective-C
8
star
20

Gym-Flappy-Bird

A OpenAI Gym Env for Flappy Bird
Python
6
star
21

songrotek.github.io

Personal Website
HTML
3
star
22

EV3Car

iPhone Control ev3 car by bluetooth
Objective-C
2
star
23

EV3PortViewer

Objective-C
1
star
24

EV3Tank

Objective-C
1
star
25

SystemSoundServices

Objective-C
1
star
26

Character-Animation-AI-Paper-List

1
star
27

tinyCNNOSX

run tiny CNN on OSX
C++
1
star