MishaLaskin/curl
CURL: Contrastive Unsupervised Representation Learning for Sample-Efficient Reinforcement Learning
This tool helps machine learning engineers and researchers quickly train reinforcement learning agents using visual observations. By taking raw pixel data from simulation environments, it efficiently learns optimal actions, producing highly performant agents that converge faster. It's ideal for those working on robotics, autonomous systems, or game AI where agents learn from images.
599 stars. No commits in the last 6 months.
Use this if you need to train reinforcement learning agents from image data and want to achieve strong performance with less training time and data.
Not ideal if your reinforcement learning problem does not involve visual inputs or if you are not working with simulation environments like DeepMind control tasks.
Stars
599
Forks
92
Language
Python
License
MIT
Category
Last pushed
Oct 28, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/MishaLaskin/curl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
cbfinn/gps
Guided Policy Search