yihaosun1124/OfflineRL-Kit

An elegant PyTorch offline reinforcement learning library for researchers.

45
/ 100
Emerging

This is a library for machine learning researchers who work with reinforcement learning. It helps you quickly experiment with existing cutting-edge offline reinforcement learning algorithms, using your existing datasets of recorded interactions to train intelligent agents. You provide your offline dataset, and the library outputs a trained policy capable of making decisions based on that data.

384 stars. No commits in the last 6 months.

Use this if you are a reinforcement learning researcher focused on developing or evaluating offline RL algorithms and need a robust, scalable, and easy-to-use framework for experimentation.

Not ideal if you are looking for a pre-built solution to deploy an agent in a live production environment or if you are not familiar with reinforcement learning concepts.

reinforcement-learning-research offline-policy-learning pytorch-ml-development algorithm-prototyping
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

384

Forks

43

Language

Python

License

MIT

Last pushed

Jul 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yihaosun1124/OfflineRL-Kit"

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