Hi, I'm Danijar! I build artificial intelligence that autonomously understands and interacts with the world.

I’m a Senior Research Scientist at Google DeepMind in San Francisco, where I lead the World Models team.

I received my PhD from the University of Toronto with Jimmy Ba as a Vanier Scholar, was a visiting student at UC Berkeley with Pieter Abbeel, and interned at Google Brain for 6 years. I completed my MRes at UCL and the Gatsby Unit with Tim Lillicrap and Karl Friston.

Contact: mail AT danijar.com

Research

My research aims at discovering the computational principles of human thinking and replicating them to build useful artificial intelligence. I approach this challenge by designing unsupervised algorithms that learn through interaction with complex environments, going beyond narrow task-specific agents.

The key questions I’m currently focusing on are:

This talk gives a technical overview of my research from a few years ago.

See YouTube for more videos.

Highlighted Work

See Google Scholar for more publications.

Short Biography

Danijar Hafner is a Research Scientist at Google Brain, where he leads the World Models team. He received his PhD from the University of Toronto with Jimmy Ba as a Vanier Scholar, was a visiting student at UC Berkeley with Pieter Abbeel, and interned at Google Brain for 6 years. He completed his MRes UCL and the Gatsby Unit with Tim Lillicrap and Karl Friston. Danijar’s research aims at building generally intelligent machines that autonomously understand and interact with the world. Towards this goal, he focuses on scaling up world models, unsupervised objectives, and deep reinforcement learning.

Twitter • Scholar • Github • LinkedIn • Google AI • ORCID

profile for danijar on Stack Exchange, a network of free, community-driven Q&A sites