Published on October 15, 2018 by

We can use deep reinforcement learning to optimize a SQL database, and in this video we’ll optimize the ordering of a series of SQL queries such that it involves the minimum possible memory/computation footprint. Deep RL involves using a neural network to approximate reinforcement learning functions, like the Q (quality) function. After we frame our database as a Markov Decision Process, I’ll use Python to build a Deep Q Network to optimize SQL queries. Enjoy!

Code for this video:
https://github.com/llSourcell/SQL_Database_Optimization

Please Subscribe! And like. And comment. That’s what keeps me going.

Want more education? Connect with me here:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology
instagram: https://www.instagram.com/sirajraval

More learning resources:

https://mldb.ai/

Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/

School of AI:
https://www.theschool.ai

And please support me on Patreon:
https://www.patreon.com/user?u=3191693

Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w

Category Tag