galilai-group/stable-worldmodel
Reliable, minimal and scalable library for evaluating and conducting world model research
This project helps robotics researchers and AI scientists efficiently evaluate and conduct experiments with 'world models'. You provide observed data from simulated environments, and it helps you train predictive models of how those environments behave. The output is a robust world model capable of predicting future states and aiding in policy learning, used by researchers focusing on reinforcement learning and model predictive control.
200 stars. Available on PyPI.
Use this if you are a researcher developing or evaluating world models for robotic control or other sequential decision-making tasks, and you need a standardized, performant toolkit for data collection, training, and evaluation.
Not ideal if you are a practitioner looking to deploy an existing, pre-trained world model into a production system, or if you are not actively involved in world model research.
Stars
200
Forks
32
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Dependencies
13
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/galilai-group/stable-worldmodel"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
NM512/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
danijar/dreamerv2
Mastering Atari with Discrete World Models
danijar/dreamerv3
Mastering Diverse Domains through World Models
danijar/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
leofan90/Awesome-World-Models
A comprehensive list of papers for the definition of World Models and using World Models for...