Skip to content

Tensorflow implementation of Deepminds dqn with double dueling networks

Notifications You must be signed in to change notification settings

fg91/Deep-Q-Learning

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

41 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Double Deep Q-Learning with Dueling Network Architecture

You find detailed explanations on the functional and underlying priciples of DQN in the notebook DQN.ipynb and the corresponding blogpost.

Requirements

  • tensorflow-gpu
  • gym
  • gym[atari] (make sure it is version 0.10.5 or higher/has BreakoutDeterministic-v4)
  • imageio
  • scikit-image

Try it yourself:

If you want to test the trained network, simply run the notebook DQN.ipynb.

If you want to train the network yourself, set TRAIN = True in the first cell of DQN.ipynb and run the notebook.

Have fun : )

About

Tensorflow implementation of Deepminds dqn with double dueling networks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published