Meta Learning and Self Play - Ilya Sutskever, OpenAI

Speaker:
Ilya Sutskever, OpenAI
Hosted by:
Vector Institute
Date and Time:
Thursday, December 14, 2017 - 12:00pm to 1:00pm
Location:
Fields Institute, Room 230

Abstract:
In the first part, I will talk about meta learning, which is the problem of training a system that quickly learns to solve a wide variety of tasks. I will present meta reinforcement learning algorithms that can quickly solve simulated robotics tasks, and show how a simple meta learning approach can address the sim2real problem in robotics.

The second part will be on self play. Self play systems provide a perfectly-fined grained curriculum, a potentially indefinite incentive for improvement, and a way of converting compute into data. I will present several recent results in self play and discuss their future potential.

Bio: Ilya Sutskever received his Ph.D. in computer science from the University of Toronto under the supervision of Geoffrey Hinton. He briefly was a postdoctoral fellow at Stanford and a co-founder of DNNResearch, which was acquired by Google. Sutskever joined the Google Brain team as a research scientist, where he developed the Sequence to Sequence model, contributed to the design of TensorFlow, and helped establish the Brain Residency Program. He is a co-founder of OpenAI, where he currently serves as research director.

Sutskever has made many contributions to the field of Deep Learning, including the first large scale convolutional neural network that convincingly outperformed all previous vision systems by winning the 2012 ImageNet competition. He was listed in MIT Technology Review’s 35 innovators under 35.
--

Edited by:
Adnan Zuberi
Program Coordinator
Fields Institute