Nature

Enhancing queries for code generation with reinforcement learning

We present a reinforcement learning framework that enhances natural language queries to improve DeepSeek code generation. A parametric refiner (Qwen with LoRA) is trained via REINFORCE while the ...
Princeton University

The Neuroscience of Reinforcement Learning

One of the most influential contributions of machine learning to understanding the human brain is the (fairly recent) formulation of learning in real world tasks in terms of the computational ...
Nature

Self-correcting quantum many-body control using reinforcement learning with tensor networks

Quantum many-body control is an essential prerequisite for the reliable operation of modern quantum technologies that are based on harnessing quantum correlations. For example, quantum computing often ...
The Conversation

What is reinforcement learning? An AI researcher explains a key method of teaching machines – and how it relates to training your dog

Understanding intelligence and creating intelligent machines are grand scientific challenges of our times. The ability to learn from experience is a cornerstone of intelligence for machines and living ...