Q-learning Function: An Introduction

When we reward our kids, or pets for perfectly carrying out an assigned task, or when we scold them for not doing what was expected of them, we are actually engaging them in a reinforcement kind of leaning; each time they are rewarded (positive reward), we are reinforcing the very action they performed, and when they are scolded (negative reward), we are discouraging that very action.

Here is an excerpt from the proposal summited to the Rockefeller foundation in 1956 by a group of ten scientist ...