Danijar Hafner
Danijar Hafner is a Staff Research Scientist at Google DeepMind in San Francisco. He received his PhD in Computer Science from the University of Toronto under Jimmy Ba and is best known for creating the Dreamer series of world model algorithms, including DreamerV1, DreamerV2, and DreamerV3, which learn behaviors through latent imagination. His research focuses on building generally intelligent machines that understand and interact with the physical world through predictive world models, artificial curiosity, and temporal abstraction.
“We leverage the Recurrent State Space Model (RSSM)... [citing] D. Hafner, T. Lillicrap, J. Ba, and M. Norouzi, 'Dream to Control: Learning Behaviors by Latent Imagination'”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.