Optimal learning guides the process of collecting information efficiently in order to provide the greatest possible value. It leverages the knowledge of experienced professionals, and works in an interactive fashion to guide the experimental process using a powerful concept called the knowledge gradient which captures the value of information.
KG "Road Map"
Do we explore? The KG map shows where we will learn the most.
Current Estimate of Objective
Do we exploit? This is the region where we think we will get the best results (but we might be wrong).
In all of these settings you learn by trial and error, whether it is in the marketplace, a laboratory, or a computer simulation. But experiments can be time consuming and expensive. You need to learn what works best, but you need to learn quickly. You need optimal learning.