Gaming the Research: Reinforcement Learning Changing Data Evaluation Challenges

Advances in artificial intelligence, specifically reinforcement learning, are proving beneficial to accelerating the pace of data-intensive challenges. The methods used by researchers with RL are techniques often used in video games, and by applying gamification to scientific processes, RL agents can learn as they are used in experiments, in effect, leveling up their rates of discovery as they work. Researchers are using trained RL agents at NSLS-II to accelerate the analysis of data-heavy measurements.

Science Snapshots From Berkeley Lab

This edition of Science Snapshots highlights the discovery of an investigational cancer drug that targets tumors caused by mutations in the KRAS gene, the development of a new library of artificial proteins that could accelerate the design of new materials, and new insight into the natural toughening mechanism behind adult tooth enamel.