Danijar Hafner on Dreamer v4

Danijar Hafner on Dreamer v4

From TalkRL: The Reinforcement Learning Podcast by Robin Ranjit Singh Chauhan

November 10, 2025 · 1h 41m · Episode 73

About this episode

Danijar Hafner discusses his work on Dreamer v4 and related research in reinforcement learning.

Danijar Hafner was a Research Scientist at Google DeepMind until recently. Featured References Training Agents Inside of Scalable World Models [ blog ] Danijar Hafner, Wilson Yan, Timothy Lillicrap One Step Diffusion via Shortcut Models Kevin Frans, Danijar Hafner, Sergey Levine, Pieter Abbeel Action and Perception as Divergence Minimization [ blog ] Danijar Hafner, Pedro A. Ortega, Jimmy Ba, Thomas Parr, Karl Friston, Nicolas Heess Additional References Mastering Diverse Domains through World Models [ blog ] DreaverV3l Danijar Hafner, Jurgis Pasukonis, Jimmy Ba, Timothy Lillicrap Mastering Atari with Discrete World Models [ blog ] DreaverV2 ; Danijar Hafner, Timothy Lillicrap, Mohammad Norouzi, Jimmy Ba Dream to Control: Learning Behaviors by Latent Imagination [ blog ] Dreamer ; Danijar Hafner, Timothy Lillicrap, Jimmy Ba, Mohammad Norouzi Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos [ Blog Post ], Baker et al

People in this episode

Guest: Danijar Hafner

Topics covered

  • Reinforcement Learning
  • Dreamer v4
  • Artificial Intelligence
  • World Models

Keywords

  • Google DeepMind
  • Research Scientist
  • Training Agents
  • Diverse Domains
  • Atari

Mentioned in this episode

Products: Dreamer v4, Dreamer v3, Dreamer v2, Dreamer

Books & works: Dream to Control: Learning Behaviors by Latent Imagination

More episodes of TalkRL: The Reinforcement Learning Podcast

Explore listener stats, chart rankings, contacts and more on the TalkRL: The Reinforcement Learning Podcast podcast page.