rubuntu / ds30_4

Brian Farris' Talk on Reinforcement Learning and Multi-Armed Bandits for the Data Incubator

Data Science in 30 Minutes: Reinforcement Learning and Multi-Armed Bandits

To view the talk that goes along with this repo, click here.

Installation Using Anaconda

Create environment

conda env create -f environment.yml

Activate environment

source activate RLtalk

Set up Twitter API credentials

In order to run the streaming Twitter examples, you will need a set of developer keys stored in a file called keys.txt. Go here to get your own credentials.

Credits

The talk was created by Brian Farris for a DS30 webinar by The Data Incubator (github). Brian Farris is a data scientist at Capital One Labs in New York. He was a Data Incubator Fellow in the Spring 2015 NYC cohort. Prior to this he was a postdoc in computational astrophysics at Columbia and NYU, working on simulations of the environments around binary black holes. He received his PhD in Physics from the University of Illinois at Urbana-Champaign.

About The Data Incubator

The Data Incubator is a data science education company based in NYC, DC, and SF with both corporate training and recruiting services. For data science corporate training, we offer customized, in-house training solutions in data and analytics. For data science hiring, we run a free 8 week fellowship training PhDs to become data scientists. The fellowship selects 2% of its 2000+ quarterly applicants and is free for Fellows. Hiring companies (including EBay, Capital One, Pfizer) pay a recruiting fee only if they successfully hire. You can read about us on Harvard Business Review, VentureBeat, or The Next Web, or read about our alumni at LinkedIn, Palantir, or the NYTimes.

For information on upcoming events, visit our Eventbrite.