
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
- Joseph Modayil of Openmind Research Institute @ RLC 2025 · January 3, 2026 · 4 min
- David Abel on the Science of Agency @ RLDM 2025 · September 8, 2025 · 60 min
- Jake Beck, Alex Goldie, & Cornelius Braun on Sutton's OaK, Metalearning, LLMs, Squirrels @ RLC 2025 · August 19, 2025 · 12 min
- Outstanding Paper Award Winners - 2/2 @ RLC 2025 · August 18, 2025 · 14 min
- Outstanding Paper Award Winners - 1/2 @ RLC 2025 · August 15, 2025 · 7 min
- Thomas Akam on Model-based RL in the Brain · August 4, 2025 · 52 min
Explore listener stats, chart rankings, contacts and more on the TalkRL: The Reinforcement Learning Podcast podcast page.