In the first chapter, the MDP reinforcement program produced a result as an output matrix. In Chapter 2, Think Like a Machine, the McCulloch-Pitts system of neurons produced an input reward matrix. However, the intermediate or final results of these two functions need to be constantly measured. Good measurement solves a substantial part of a given problem since decisions rely on them. Reliable decisions are made with reliable evaluations. The goal of this chapter is to introduce measurement methods.
The key function of human intelligence, decision-making, relies on the ability to evaluate a situation. No decision can be made without measuring the pros and cons and factoring the parameters.
Mankind takes great pride in its ability to evaluate. However, in many cases, a machine can do better. Chess represents the pride of mankind in thinking...
