John Langford @ ZEFR
John Langford is a Principal Researcher at Microsoft and the primary author of Vowpal Wabbit. Come join us as he discusses applications of reinforcement learning.
NOTE: This is the first Meetup we've done on a weekend. Please RSVP if you can come as I want to make sure we'll have a high enough attendance.
6:30 PM Doors open
6:30 PM - 7:00 PM Snack and drinks served
7:00 PM - 8:00 PM Presentation and Q&A
8:00 PM - 8:30 PM Mingling
8:30 PM Doors close
Title: Real World Reinforcement Learning
We have been developing the tools to apply reinforcement learning to real world problems including many working applications in personalization, system optimization, and wellness. I’ll discuss contextual bandit (=one step RL) fundamentals, the tools we have to make this new class of applications routine, and a few war stories 😊 In addition, I’ll give an overview of where I see future real world RL applications developing.
John Langford is a machine learning research scientist, a field which he says "is shifting from an academic discipline to an industrial tool". He is the author of the weblog hunch.net and the principal developer of Vowpal Wabbit. John works at Microsoft Research New York, of which he was one of the founding members, and was previously affiliated with Yahoo! Research, Toyota Technological Institute at Chicago, and IBM's Watson Research Center. He studied Physics and Computer Science at the California Institute of Technology, earning a double bachelor's degree in 1997, and received his Ph.D. in Computer Science from Carnegie Mellon University in 2002. He was the program co-chair for the 2012 International Conference on Machine Learning.
Parking and directions:
There is street parking in the neighborhood east of Redwood Ave. Please enter through the doors at 4101 Redwood Ave.