Hi, I'm Danijar! I build intelligent machines that autonomously understand and interact with the physical world.

Contact: mail AT danijar.com

I’m a Research Scientist at Google DeepMind in San Francisco. My research aims at building generally intelligent machines that understand and interact with the world, focusing on these key questions:

• World Models Learning powerful predictive models that equip AI with a deep understanding of the physical world and enable planning by imagining the future.
  Key papers: DreamerV3, DayDreamer, PlaNet, TECO, Dynalang

• Temporal Abstraction Achieving long-term tasks by breaking them down into subgoals that enable abstract planning and are realized through low-level actions.
  Key papers: Director, Latent Skill Planning, Clockwork VAE

• Scalable Objectives Designing objectives for AI to self-improve beyond human input, such as by autonomously exploring and practicing open ended goals.
  Key papers: Action Perception Divergence, Plan2Explore, LEXA, VIPER

Featured Media

See YouTube for more videos.

• Learning to Walk in the Real World in 1 Hour
• AI Masters Minecraft
• Interview on World Models
• Interview in Daily Mail

• Interview in MIT Technology Review

• Lab Spotlight in Tech Crunch

• Unsupervised Intelligent Agents Technical Talk
• Open-Endedness Panel
• Talk RL Podcast
• Introducing Director

• Introducing Dreamer

• Introducing Plan2Explore

Highlighted Work

See Google Scholar for more publications.

• 

  Mastering Diverse Control Tasks through World Models

  D Hafner, J Pasukonis, J Ba, T Lillicrap

  Nature

  Paper Twitter Code

• 

  One Step Diffusion via Shortcut Models

  K Frans, D Hafner, S Levine, P Abbeel

  ICLR 2025 (oral, 1.5%)

  Paper Website Code

• 

  Learning to Model the World with Language

  J Lin, Y Du, O Watkins, D Hafner, P Abbeel, D Klein, A Dragan

  ICML 2024 (oral)

  Paper Website Twitter

• 

  Video Prediction Models as Rewards for Reinforcement Learning

  A Escontrela, A Adeniji, W Yan, A Jain, X B Peng, K Goldberg, Y Lee, D Hafner, P Abbeel

  NeurIPS 2024

  Paper Website Twitter

• 

  Evaluating Long-Term Memory in 3D Mazes

  J Pasukonis, T Lillicrap, D Hafner

  ICLR 2023

  GitHub Paper Twitter

• 

  Temporally Consistent Transformers for Video Generation

  W Yan, D Hafner, S James, P Abbeel

  ICML 2023

  GitHub Paper Twitter Videos

• 

  DayDreamer: World Models for Physical Robot Learning

  P Wu*, A Escontrela*, D Hafner*, K Goldberg, P Abbeel

  CoRL 2022

  Paper Twitter Talk Code Robot Parts

• 

  Deep Hierarchical Planning from Pixels

  D Hafner, K Lee, I Fischer, P Abbeel

  NeurIPS 2022

  Blog Paper Twitter Talk Code

• 

  Discovering and Achieving Goals via World Models

  R Mendonca*, O Rybkin*, K Daniilidis, D Hafner, D Pathak

  NeurIPS 2021 (26%), URL 2021 (oral), SSL 2021 (oral)

  Paper Poster Website Twitter Code Envs

• 

  Benchmarking the Spectrum of Agent Capabilities

  D Hafner

  ICLR 2022, DRLW 2021 (oral)

  GitHub Paper Poster Twitter

• 

  Clockwork Variational Autoencoders

  V Saxena, J Ba, D Hafner

  NeurIPS 2021 (26%)

  Paper Poster Twitter Dataset Code

• 

  Latent Skill Planning for Exploration and Transfer

  K Xie, H Bharadhwaj, D Hafner, A Garg, F Shkurti

  ICLR 2021 (28%)

  Paper Videos

• 

  Mastering Atari with Discrete World Models

  D Hafner, T Lillicrap, M Norouzi, J Ba

  ICLR 2021 (28%)

  Blog Paper Twitter Poster Code

• 

  Action and Perception as Divergence Minimization

  D Hafner, P Ortega, J Ba, T Parr, K Friston, N Heess

  DRLW 2020

  Paper Twitter Poster FAQs

• 

  Planning to Explore via Self-Supervised World Models

  R Sekar, O Rybkin, K Daniilidis, P Abbeel, D Hafner, D Pathak

  ICML 2020 (22%)

  Blog Paper Code Twitter Talk Website

• 

  Dream to Control: Learning Behaviors by Latent Imagination

  D Hafner, T Lillicrap, J Ba, M Norouzi

  ICLR 2020 (oral, 4%), DRLW 2019 (oral)

  Blog Paper Twitter Poster Videos Code

• 

  A Deep Learning Framework for Neuroscience

  Richards, Lillicrap, Beaudoi, Bengio, Bogacz, Christensen, Clopath, Costa, Berker, Ganguli, Gillon, Hafner, Kepecs, Kriegeskorte, Latham, Lindsay, Miller, Naud, Pack, Poirazi, Roelfsema, Sacramento, Saxe, Scellier, Schapiro, Senn, Wayne, Yamins, Zenke, Zylberberg, Therien, Kording

  Nature Neuroscience

  Paper Twitter

• 

  Noise Contrastive Priors for Functional Uncertainty

  D Hafner, D Tran, A Irpan, T Lillicrap, J Davidson

  UAI 2019 (26%)

  Paper Poster Code

• 

  Learning Latent Dynamics for Planning from Pixels

  D Hafner, T Lillicrap, I Fischer, R Villegas, D Ha, H Lee, J Davidson

  ICML 2019 (23%)

  Blog Paper Poster Code

• 

  Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion

  J Buckman, D Hafner, G Tucker, E Brevdo, H Lee

  NeurIPS 2018 (oral, 0.6%)

  Paper Poster Talk Code

• 

  Sim-to-Real: Learning Agile Locomotion For Quadruped Robots

  J Tan, T Zhang, E Coumans, A Iscen, Y Bai, D Hafner, S Bohez, V Vanhoucke

  RSS 2018 (31%)

  Paper

Short Biography

Danijar Hafner is a Research Scientist at Google DeepMind. He received his PhD at the University of Toronto with Jimmy Ba, was a visiting student at UC Berkeley with Pieter Abbeel, was a Vanier Scholar, and interned at Google Brain for many years. He completed his MRes at UCL and the Gatsby Unit with Tim Lillicrap and Karl Friston. Danijar’s research aims at building generally intelligent machines that understand and interact with the world.

Twitter • Scholar • Github • LinkedIn • ORCID