yihaosun1124/OfflineRL-Kit
An elegant PyTorch offline reinforcement learning library for researchers.
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.
Stars
384
Forks
43
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild