Beat Atari with Deep Reinforcement Learning! (Part 1: DQN)


In this post, we will attempt to reproduce the following paper by DeepMind: Playing Atari with Deep Reinforcement Learning, which introduces the notion of a Deep Q-Network.

I strongly recommend that you skim through the paper before reading this tutorial, and then read it more deeply when you are done. I will be quoting it throughout. Further, I recommend you really do try to implement your DQN from what I am writing here.

View full post here

In the event you would want to cite this blog post, you could use this template:

  title={Beat Atari with Deep Reinforcement Learning! (Part 1: DQN)},
  author={Ecoffet, Adrien},
  url = {},