takuseno/d3rlpy
An offline deep reinforcement learning library
This is a library for developing and testing deep reinforcement learning agents that can learn from pre-recorded data or through direct interaction. It takes in datasets of past interactions or a simulated environment, and outputs trained agents capable of making decisions or controlling systems. This is ideal for machine learning engineers and researchers focused on building intelligent decision-making systems.
1,644 stars. No commits in the last 6 months. Available on PyPI.
Use this if you need to build advanced decision-making agents, particularly in situations where direct interaction during training is costly or impossible, such as in robotics or medical applications.
Not ideal if you are looking for a simple, off-the-shelf solution without requiring customization or an understanding of deep reinforcement learning principles.
Stars
1,644
Forks
263
Language
Python
License
MIT
Category
Last pushed
Sep 10, 2025
Commits (30d)
0
Dependencies
11
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/takuseno/d3rlpy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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