RESEARCH PAPERYear 2024

Genie: Generative Interactive Environments

View all authors

Jake Bruce; Michael D Dennis; Ashley Edwards; Jack Parker-Holder; Yuge Shi; Edward Hughes; Matthew Lai; Aditi Mavalankar; Richie Steigerwald; Chris Apps; Yusuf Aytar; Sarah Maria Elisabeth Bechtle; Feryal Behbahani; Stephanie C.Y. Chan; Nicolas Heess; Lucy Gonzalez; Simon Osindero; Sherjil Ozair; Scott Reed; Jingwei Zhang; Konrad Zolna; Jeff Clune; Nando De Freitas; Satinder Singh; Tim Rocktäschel

Classification

View four quadrants
Architecture
Not applicable
Prediction paradigm
Not applicable
Source review status
Verified from primary sources

Category review. Genie assembles a video tokenizer, latent-action model and dynamics transformer into an interactive learned environment. At interaction time the user chooses latent codes and the model generates frames; the separately calibrated imitation experiment does not turn the general simulator into a canonical encoder/backbone. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX