nuomizai/HIL-RL

Human in the loop Reinforcement Learning suite

FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control

[Science Robotics 2026] Official Implementation of the paper RL-100

A framework for Reinforcement Learning research.

Official implementation of Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration

robomimic: A Modular Framework for Robot Learning from Demonstration

Customizable Reinforcement Learning

A unified framework for robot learning

What Enables In-Context Behavior Prompting for Manipulation?