CSD/ML Faculty Candidate
— 12:00pm
Location:
In Person and Virtual - ET
-
Newell-Simon 4305 and Zoom
Speaker:
DANIJAR HAFNER
,
Ph.D. Candidate, Department of Computer Science, University of Toronto
https://danijar.com/
Embodied Intelligence Through World Models
Deep learning has proven to be a powerful tool for prediction and generation across many domains, including text, images, audio, and video. However, fully automating tasks requires machines to make autonomous decisions, for which traditional algorithms require impractical amounts of data and supervision. Analogous to the success of unsupervised learning in other fields, I argue that the future of decision making will be foremost unsupervised. Towards this vision, I introduce the Dreamer algorithm for learning accurate world models and using them for successful decision making.
This algorithm is the first to solve the Minecraft Diamond Challenge from scratch and to teach a physical robot dog to stand up and walk in 1 hour without simulators. Leveraging learned world models, I will then introduce algorithms for autonomous exploration and temporally-abstract decision making that further reduce the amount of supervision. Looking forward, these algorithms pave the way to foundation models for decision making and a broad range of applications.
—
Danijar Hafner is a PhD candidate in artificial intelligence at the University of Toronto with Jimmy Ba and a visiting student at the University of California, Berkeley with Pieter Abbeel. He is also a research scientist intern at DeepMind. Danijar’s research aims at building intelligent machines based on the computational principles of the brain. Towards this goal, he focuses on scaling up embodied artificial intelligence through general world models, unsupervised objectives, and deep reinforcement learning. Danijar completed his MRes in Computational Statistics and Machine Learning at UCL with Tim Lillicrap and Karl Friston. His work is supported by Canada’s Vanier Scholarship.
Faculty Hosts: Zico Kolter, Barnabás Póczos In Person and Zoom Participation. See announcement.