Before getting into Q-Learning, lets understand the importance concept of Exploration vs Exploitation. Exploration is trying new possibilities in order to find better rewards. Exploitation is to keep opting for same actions that has given some significant rewards in the past. To illustrate this we can consider an example of restaurants. Suppose i recently start living in a new city.

LDV Capital, a venture capital firm focussed on Visual Technologies, recently published a 19 page report thick with some pretty eye opening data around cameras. Specifically, how many cameras we can expect to have watching us, what they are watching us for, and how those insights will be used. According to their study, by 2022 there will be more than 44,354,881,622 [1] (that's 44 BILLION) cameras in use globally, collecting even more billions of images for visual collateral. This is incredible -- but what's interesting -- is that most of these images will never be seen by human eyes. This forecast is a revelation that our use of cameras is evolving into something markedly different than the random Snapchat clips and candid family memories of now.

You fire up a ridesharing app to head out to your favorite restaurant. But then an ad appears, offering a free ride to a new Thai spot on the other side of town. Suddenly, you're reconsidering plans: Why pay for a ride to one neighborhood when another is totally free? Ultimately, your favorite restaurant could lose a customer. Scenarios like this may play out in the coming era of self-driving vehicles.

Imagine if everything around you was connected and A.I.-enabled. Ordering at your favorite restaurants would be as simple as sending them a text. Your dry cleaner would know exactly when to pick up your laundry without you uttering a word. And when you run low on groceries, your refrigerator would order food for you. This fully integrated world is right around the corner.