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 Computational Statistics and Machine Learning at UCL and the Gatsby Unit with Tim Lillicrap and Karl Friston. My work is supported by the Vanier Scholarship.
Preferred way of being contacted: [email protected]
The goal of my research is to discover the computational principles of human thinking by building intelligent machines that learn through interaction with complex simulated worlds. Within deep reinforcement learning, my work focuses on:
- Unsupervised world models learned from raw video data for artificial intelligence to develop a general understanding of the world and plan by imagining future outcomes of actions. The main challenges here are representation learning and temporal abstraction.
- Unsupervised agent objectives to autonomously explore and influence the environment, moving artificial intelligence beyond narrow task-specified behaviors. This includes artificial curiosity, information gain, empowerment, skill discovery, and active inference.
You can hear more on the TalkRL Podcast and on my research page.
See Google Scholar for more publications.
Clockwork Variational Autoencoders
Evaluating Agents without Rewards
BARL 2020 (oral)
Latent Skill Planning for Exploration and Transfer
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
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%)
Danijar Hafner is a PhD student at the University of Toronto advised by Jimmy Ba and Geoffrey Hinton. He is also a 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.