Learning Latent Dynamics for Planning from Pixels

·David Ha (Otoro)··

--> --> --> Evolved Biped Walker.--> PlaNet learns a world model from image inputs only and successfully leverages it for planning in latent space. GitHub --> Redirecting to planetrl.github.io, where the article resides. console.log('redirect.'); window.location.href = "https://planetrl.github.io/";

Read full article →

Related Articles

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 2mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 2mo ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 2mo ago
Show HN: I trained a language model that thinks the capital of Japan is Paris
farisallafi · Hacker News · 9h ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 2mo ago