Google recently released a research framework for fast prototyping of reinforcement learning algorithms called "Dopamine". They say that it aims to fill the need for a small, easily grokked codebase in which users can freely experiment with wild ideas (speculative research). In this live stream i'll test it out, try out a few basic reinforcement learning algorithms and compare it to similar frameworks. You can code along with me using CoLab. Get hype!
Code for this video:
https://github.com/llSourcell/Google_Dopamine_LIVE
Please Subscribe! And like. And comment. That's what keeps me going.
The School of AI:
https://www.theschool.ai
Want more education? Connect with me here:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology
instagram: https://www.instagram.com/sirajraval
Github Syllabus:
https://github.com/llSourcell/Move_37_Syllabus
More learning resources:
https://github.com/google/dopamine
https://ai.googleblog.com/2018/08/introducing-new-framework-for-flexible.html
https://joshgreaves.com/reinforcement-learning/understanding-rl-the-bellman-equations/
https://www.youtube.com/watch?v=N0Ld2iTMaMs
Join us in the Wizards Slack channel:
http://wizards.herokuapp.com/
And please support me on Patreon:
https://www.patreon.com/user?u=3191693
