Danijar Hafner (@danijarh) / X

Danijar Hafner

2,712 posts

Danijar Hafner

@danijarh

Building AI that autonomously understands and interacts with the world. Previous: @GoogleDeepMind @UCBerkeley @UofT

Joined August 2013

Pinned
Danijar Hafner
@danijarh
Sep 30, 2025
Excited to introduce Dreamer 4, an agent that learns to solve complex control tasks entirely inside of its scalable world model! 🌎🤖 Dreamer 4 pushes the frontier of world model accuracy, speed, and learning complex tasks from offline datasets. co-led with @wilson1yan
00:00
456K
Danijar Hafner
@danijarh
Oct 25, 2025
Congratulations @Yoshua_Bengio!! Possibly the first scientist with one million citations in the world. Crazy how fast the field has grown 🤯
725K
Danijar Hafner
@danijarh
Aug 5, 2019
What I value most about Jupyter notebooks is having all results and figures together in a doc. Today I'm releasing Python Handout, a package that lets you create docs with inline figures, images, videos directly from Python scripts. ✨ 📰 ✨ github.com/danijar/handout Thread 👇
Danijar Hafner
@danijarh
Nov 3, 2025
Today is my last day at @GoogleDeepMind. After almost exactly 10 years at Google including 12 internships and the last 2 1/2 years full time, it really feels like a chapter coming to an end. I'm grateful for all the experiences and friends I've made at Google and DeepMind. I
292K
Danijar Hafner
@danijarh
Jul 6, 2022
The full training run of the A1 quadruped robot learning to walk from scratch in the real world in 1 hour! Made possible by training a world model online and planning inside of it. Excited to see what we can do next with this! @philippswu @AleEscontrela @Ken_Goldberg @pabbeel
00:00
Danijar Hafner
@danijarh
Jan 11, 2023
Excited to announce DreamerV3 🌍, a scalable and general RL algorithm that masters a wide range of applications with fixed hyperparameters! Applied out of the box, it solves the Minecraft Diamond challenge without human data. 💎 👇 Thread
451K
Danijar Hafner
@danijarh
Apr 2, 2025
Excited to share that DreamerV3 has been published in Nature! Dreamer solves control tasks by imagining the future outcomes of its actions inside of a continuously learned world model 🌏 It's the first agent to find diamonds in Minecraft from scratch without human data! 💎 👇
109K
Danijar Hafner
@danijarh
Apr 22, 2021
DreamerV2 learns a world model of the DeepMind humanoid and solves standup and walking from only pixel inputs 🌍🚀
GIF
Danijar Hafner
@danijarh
Jun 29, 2022
A dream come true! We introduce DayDreamer, where we apply world models for fast end-to-end learning on 4 physical robots, without simulators. We learn quadruped walking from scratch in 1 hour. We also learn to pick & place balls directly from pixels and sparse rewards 🤖🌏👇
GIF
Danijar Hafner
@danijarh
Jun 10, 2022
Excited to share Director, a practical, general, and interpretable reinforcement learning algorithm for learning hierarchical behaviors from pixels! Director explores and solves long-horizon tasks with very sparse rewards by breaking them down into internal subgoals. Thread 👇
00:00
Danijar Hafner
@danijarh
Oct 6, 2025
SOTA humanoid locomotion: 20M params Fruit fly: 50M params
Massimo
@Rainmaker1973
Oct 5, 2025
Scientists have mapped the entire neural network of the fruit fly. 50 million synapses between 139,000 neurons.
Avraham Z. Cooper, MD 🩺
00:00
Avraham Z. Cooper, MD 🩺
53K
Danijar Hafner
@danijarh
Feb 23, 2021
Excited to present Clockwork VAEs for video prediction! Clockwork VAEs (CW-VAEs) leverage hierarchies of latent sequences, where higher levels tick slower. They learn long-term deps across 1000 frames, semantically separate content, and outperform strong video models. 👇 Thread
GIF
Danijar Hafner
@danijarh
Oct 7, 2020
World models are the future and the future is now! 🌎🚀 Proud to share DreamerV2, the first agent that achieves human-level Atari performance by learning behaviors purely within a separately trained world model. Paper: arxiv.org/pdf/2010.02193… Thread 👇
Danijar Hafner
@danijarh
Aug 4, 2023
Excited to introduce Dynalang, an interactive agent that understands diverse types of language in visual environments! 🤖💬 By learning a multimodal world model 🌍, Dynalang understands task prompts, corrective feedback, simple manuals, hints about out of view objects, and more
00:00
69K