MishaLaskin/rad
RAD: Reinforcement Learning with Augmented Data
This project helps machine learning engineers improve the training efficiency and performance of their reinforcement learning agents. It takes raw visual observations from simulated environments and applies various data augmentation techniques to them. The output is a more robustly trained reinforcement learning agent capable of performing tasks more effectively in complex environments.
416 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer working on reinforcement learning tasks and want to train more capable agents with less data and computational resources, especially from visual inputs.
Not ideal if you are looking for a general-purpose machine learning library or if your reinforcement learning problem does not involve image-based observations.
Stars
416
Forks
75
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 29, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MishaLaskin/rad"
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