Hi, I am a PhD student in artificial intelligence at the University of
Toronto with Jimmy Ba and Geoffrey Hinton and a
researcher at Google Brain and the Vector Institute. I
completed my MRes in CSML at University College London with Tim
Lillicrap and Karl Friston. In the past, I’ve done a lot
of software engineering.
My goal is to understand the computational principles behind human thinking by replicating them in complex environments. My current research focuses on deep learning, world models, and unsupervised reinforcement learning. You can hear more about my research on the TalkRL Podcast. My work is supported by the Vanier Scholarship.
If you have any questions, feel free to contact me: [email protected]
Selected research
Please see my Scholar profile for a full list.
-
Evaluating Agents without Rewards
BARL 2020 (oral) -
Skill Transfer via Partially Amortized Hierarchical Planning
ICLR 2021 (28%) -
Mastering Atari with Discrete World Models
ICLR 2021 (28%) -
-
Planning to Explore via Self-Supervised World Models
ICML 2020 (22%) -
Dream to Control: Learning Behaviors by Latent Imagination
ICLR 2020 (oral, 4%), DRLW 2019 (oral) -
A Deep Learning Framework for Neuroscience
Nature Neuroscience -
Noise Contrastive Priors for Functional Uncertainty
UAI 2019 (26%) -
Learning Latent Dynamics for Planning from Pixels
ICML 2019 (oral, 23%) -
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
NeurIPS 2018 (oral, 0.6%) -
Sim-to-Real: Learning Agile Locomotion For Quadruped Robots
RSS 2018 (oral, 31%)
Students
If you would like to work together on a research project, please see this form for more information and to submit your application. I highly encourage applications from candidates of underrepresented groups and with unconventional backgrounds.
Current
-
Minghan Li
MSc
next: Waterloo PhD
-
Vaibhav Saxena
MSc
-
Brendon Matusch
High School
next: Stanford BSc
Former
-
Calvin Luo
BSc
next: Google AI Resident
Short biography
Danijar Hafner is a PhD student at the University of Toronto advised by Jimmy Ba and Geoffrey Hinton. He is also a student researcher at Google Brain and the Vector Institute. His research focuses on artificial intelligence, specifically on deep learning, world models, and unsupervised reinforcement learning. Danijar completed his MRes at the University College London and the Gatsby Unit under the supervision of Tim Lillicrap and Karl Friston. He completed his bachelor’s thesis on deep reinforcement learning for the video game Doom at the Hasso Plattner Institute, Germany.