denisyarats/drq
DrQ: Data regularized Q
This project helps researchers in reinforcement learning train agents for complex tasks, especially those that rely on visual input. It takes raw image data from a simulation or environment and outputs a highly performant, stable learning agent. This is for machine learning researchers and practitioners focused on developing and evaluating advanced AI agents.
419 stars. No commits in the last 6 months.
Use this if you are a researcher or engineer working on deep reinforcement learning from pixels and need a robust, state-of-the-art method to improve agent training efficiency and performance.
Not ideal if you are looking for a general-purpose, easy-to-use reinforcement learning library for high-level application development rather than research into core algorithms.
Stars
419
Forks
54
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Jan 13, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/denisyarats/drq"
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