MishaLaskin/curl

CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning

48
/ 100
Emerging

This tool helps machine learning engineers and researchers quickly train reinforcement learning agents using visual observations. By taking raw pixel data from simulation environments, it efficiently learns optimal actions, producing highly performant agents that converge faster. It's ideal for those working on robotics, autonomous systems, or game AI where agents learn from images.

599 stars. No commits in the last 6 months.

Use this if you need to train reinforcement learning agents from image data and want to achieve strong performance with less training time and data.

Not ideal if your reinforcement learning problem does not involve visual inputs or if you are not working with simulation environments like DeepMind control tasks.

Reinforcement Learning Robotics Simulation Autonomous Systems Training AI Agent Development Image-based Control
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 22 / 25

How are scores calculated?

Stars

599

Forks

92

Language

Python

License

MIT

Last pushed

Oct 28, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MishaLaskin/curl"

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