New challenges in Reinforcement Learning: Dr. O. Vinyals (Google DeepMind)
Details
https://secure.meetupstatic.com/photos/event/e/3/e/1/600_464458337.jpeg
Deep Learning & AI has joined forces with the Qualcomm - UvA lab (https://ivi.fnwi.uva.nl/quva/) and we're excited to present this next Deep Vision Seminar with an international speaker.
Oriol Vinyals (https://research.google.com/pubs/OriolVinyals.html) is a Research Scientist at Google. He works in deep learning with Google DeepMind -- previously he was a member of the Google Brain team.
He holds a Ph.D. in EECS from University of California, Berkeley, and a Masters degree from the University of California, San Diego.
Amongst others, he has been voted by MIT Technology Review as one of the coming Innovators Under 35, once ranked as the top StarCraft player in Spain (https://www.technologyreview.com/lists/innovators-under-35/2016/pioneer/oriol-vinyals/) and currently involved in a joint lab with Blizzard to have StarCraft II as an AI Research Environment (https://deepmind.com/blog/deepmind-and-blizzard-release-starcraft-ii-ai-research-environment/).
Location: The seminar will be held on September 15, 14:00-15:00, Room C1.110, Science Park 904. (https://rooster.uva.nl/locationinfo/645C1110)
Title: New challenges in Reinforcement Learning
Abstract: In this talk Oriol will describe some of the recent work that he and his collaborators have done at DeepMind in model based RL, and their recent work on StarCraft II, a strategy game which poses a new challenge for deep RL.
Bio: Oriol Vinyals is a Staff Research Scientist at Google DeepMind, working in Deep Learning. Prior to joining DeepMind, Oriol was part of the Google Brain team. He holds a Ph.D. in EECS from University of California, Berkeley and is a recipient of the 2016 MIT TR35 innovator award. At DeepMind he continues working on his areas of interest, which include artificial intelligence, with particular emphasis on sequences, deep learning and reinforcement learning.