myscience/open-genie

Pytorch implementation of "Genie: Generative Interactive Environments", Bruce et al. (2024).

44
/ 100
Emerging

This project helps researchers and developers create interactive AI environments from unlabeled video footage. It takes raw video data and processes it into a format that allows an AI model to learn actions and predict how those actions will affect future video frames. The primary users are AI/ML researchers focused on generative models and unsupervised learning for interactive systems.

267 stars. No commits in the last 6 months.

Use this if you are an AI researcher looking to train generative interactive AI models on large datasets of unlabelled internet videos to simulate dynamic environments and agent interactions.

Not ideal if you need a plug-and-play solution for game development or a pre-trained model for immediate use in production, as this is a research-focused implementation requiring significant setup and training.

generative-AI unsupervised-learning interactive-environments video-synthesis AI-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

267

Forks

36

Language

Python

License

MIT

Last pushed

Aug 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/myscience/open-genie"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.