Summary
This was a short but intense chapter in which we spent time looking at various third-party DRL frameworks. Fortunately, all of these frameworks are all still free and open source, and let's hope they stay that way. We started by looking at the many growing frameworks and some pros and cons. Then, we looked at what are currently the most popular or promising libraries. Starting with Google Dopamine, which showcases RainbowDQN, we looked at how to run a quick sample of Google Colab. After that, Keras-RL was next, and we introduced ourselves to the Keras framework as well as how to use the Keras-RL library. Moving on to RLLib, we looked at the powerful automation of the DRL framework that has many capabilities. Finally, we finished up ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access