CJReinforce/RIME_ICML2024
Official code for ICML 2024 paper, "RIME: Robust Preference-based Reinforcement Learning with Noisy Preferences" (ICML 2024 Spotlight)
This project helps machine learning researchers and engineers train reinforcement learning agents using human feedback, even when those preferences are inconsistent or noisy. It takes in human preferences about an agent's behavior and outputs a more robustly trained agent. This is designed for those working with preference-based reinforcement learning.
No commits in the last 6 months.
Use this if you are developing AI agents and need to train them effectively with human feedback, especially when dealing with potentially unreliable or inconsistent human judgments.
Not ideal if you are looking for a pre-trained agent or a solution that doesn't involve custom model training and hyperparameter tuning.
Stars
36
Forks
4
Language
Python
License
MIT
Category
Last pushed
Oct 15, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/CJReinforce/RIME_ICML2024"
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