Reinforcement Learning: A beginners guide to multi-arm bandits

Subscribe to the channels here:
YouTube: https://www.youtube.com/setuchokshi
Twitch: https://www.twitch.tv/setuchokshi/
Twitter: https://twitter.com/setuc
Periscope: https://www.periscope.tv/setuc/

Over the past few streams, we have talked a lot about the ideas around Reinforcement Learning. Based on the feedback, we decided to do a session for absolute beginners. We will use this approach to build the concepts for Reinforcement Learning using multi arm bandit methods and then go deeper into various algorithms (part 2). We will also cover ideas in contextual bandits (part 3) and end the series with a hands-on azure personalizer (part 4).

This is a hands-on session and the first 15 users to logon and subscribe to the channel on YouTube or Twitch will get access to Visual Studio Online to do the hands-on while I stream. All this with live support. The coding will be done in Python and you are welcome to follow along.

I am suggesting to subscribe, so you know exactly which video is going live and you get an alert. With the users on twitch and youtube, there is a way to interact and answer questions in real-time.