Beat Atari with Deep Reinforcement Learning! (Part 0: Intro to RL)


In late 2013, a then little-known company called DeepMind achieved a breakthrough in the world of reinforcement learning: using deep reinforcement learning, they implemented a system that could learn to play many classic Atari games with human (and sometimes superhuman) performance.

While their achievement was certainly quite impressive and required massive amounts of insights to discover, it also turns out that deep reinforcement learning is also quite straightforward to understand. Further, recent libraries such as OpenAI gym and keras have made it much more straightforward to implement the code behind DeepMindā€™s algorithm. In this series, you will learn to implement it and many of the improvements that came after.

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 0: Intro to RL)},
  author={Ecoffet, Adrien},
  url = {},