GitHub

verl: Volcano Engine Reinforcement Learning for LLMs

verl is a flexible, efficient and production-ready RL training library for large language models (LLMs). verl is the open-source version of HybridFlow: A Flexible and Efficient RLHF Framework paper.
IEEE

DNOperNet: A Generic Network Architecture for Scalable and Safe Deep Reinforcement Learning in Distribution Network Operation

Abstract: With the growing penetration of distributed energy resources (DERs) in distribution networks (DNs), the volatility and uncertainty make it increasingly challenging for DNs to operate. In ...
IEEE

A Generalist Agent Learning Architecture for Versatile Quadruped Locomotion

Abstract: Quadrupeds can generate various motor behaviors with the muscle synergies activated by the central nervous system. However, versatile locomotion for quadruped robots remains challenging due ...