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.
Microsoft

UniRG: Scaling medical imaging report generation with multimodal reinforcement learning

AI can be used to produce clinically meaningful radiology reports using medical images like chest x-rays. Medical image report generation can reduce reporting burden while improving workflow ...
Microsoft

Agent Lightning: Adding reinforcement learning to AI agents without code rewrites

AI agents are reshaping software development, from writing code to carrying out complex instructions. Yet LLM-based agents are prone to errors and often perform poorly on complicated, multi-step tasks ...
IEEE

Deep Reinforcement Learning for Distribution System Operations: A Tutorial and Survey

The rapid evolution of modern electric power distribution systems into complex networks of interconnected active devices, distributed generation (DG), and storage poses increasing difficulties for ...
blockchain

PyTorch for Deep Learning Professional Certificate Launches: Advanced AI Skills and Deployment Training

According to DeepLearning.AI (@DeepLearningAI), the new PyTorch for Deep Learning Professional Certificate, led by Laurence Moroney, provides in-depth, practical training on building, optimizing, and ...
C&EN

Hierarchical Reinforcement Learning with Dynamic Meta Agent for Adaptive Cut Selection in Integer Programming with Applications to Sensor Network Design

Department of Chemical Engineering, Indian Institute of Technology Delhi, Hauz Khas, New Delhi 110016, India Indian Institute of Technology Delhi-Abu Dhabi, Khalifa City B 20010, Abu Dhabi, UAE ...