Skip to content
/ tetris-ai-deep-reinforcement-learning Public

Deep Reinforcement Learning (RL) Tetris AI using Value Function based learning and hand crafted features

3 stars 1 fork Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

andreanlay/tetris-ai-deep-reinforcement-learning

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
demo
demo
 
 
model
model
 
 
src
src
 
 
README.md
README.md
 
 
diagram.png
diagram.png
 
 

Repository files navigation

Tetris AI Deep Q-Learning

Basic applications of Deep Reinforcement Learning for playing Tetris

Full video link

Deep Q Network Architecture

Hand Engineered Features

  1. Cleared Lines
  2. Bumpiness (Sum of height difference between each column)
  3. Holes (Space with block on top of it)
  4. Sum of heights

Prerequisites

  • Python 3.8
  • Tensorflow 2.1.1
  • Keras 2.4.0
  • OpenCV 4.3.0

About

Deep Reinforcement Learning (RL) Tetris AI using Value Function based learning and hand crafted features

Topics

deep-neural-networks qlearning deep-reinforcement-learning

Resources

Readme
Activity

Stars

3 stars

Watchers

0 watching

Forks

1 fork
Report repository

Releases

No releases published

Packages

No packages published

Languages