• Martin Thoma
  • Home
  • Categories
  • Tags
  • Archives
  • Support me

DQN - Deep Q Networks

Contents

  • DQN - Deep Q Networks
    • Results
    • See also

This blog post is a collection of experiments, not for explaining. If you want to understand how DQNs work, have a look at keon.io/deep-q-learning. Another one is DQN and OpenAI Cartpole.

Results

The code is dqn_agent.py on Github.

Environment Config File Time Score
CartPole-v0

See also

  • matthiasplappert/keras-rl
  • devsisters/DQN-tensorflow

Published

Nov 30, 2017
by Martin Thoma

Category

Machine Learning

Tags

  • Machine Learning 81
  • Reinforcement Learning 7

Contact

  • Martin Thoma - A blog about Code, the Web and Cyberculture
  • E-mail subscription
  • RSS-Feed
  • Privacy/Datenschutzerklärung
  • Impressum
  • Powered by Pelican. Theme: Elegant by Talha Mansoor