Shalev-Lifshitz/STEVE-1

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

30
/ 100
Emerging

This project offers an AI model that can understand text instructions and perform corresponding actions within the Minecraft game environment. You provide simple text commands, and the AI agent then navigates and interacts within Minecraft using low-level controls like mouse and keyboard, based on raw pixel inputs. This is for researchers or game developers interested in creating more intuitive and adaptive AI agents for virtual worlds.

204 stars. No commits in the last 6 months.

Use this if you are a researcher or developer exploring how to train AI agents to follow open-ended text instructions in complex simulated environments like video games, with a focus on generative behavior.

Not ideal if you're looking for a ready-to-use, consumer-facing Minecraft mod or tool, as this is a research model requiring technical setup and expertise.

AI-research game-AI reinforcement-learning generative-models Minecraft-automation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 8 / 25
Community 12 / 25

How are scores calculated?

Stars

204

Forks

16

Language

Python

License

Last pushed

Jun 04, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/Shalev-Lifshitz/STEVE-1"

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