In Part 1 we tried to bring order to chaos using PCA and SVD.

My bubbe kept every piece of information she had ever received. Every receipt, every letter, every grudge — all of it, organised in a system that made perfect sense to her and to nobody else on earth. You’d ask her one simple question and she’d hand you fourteen folders and a story about something your uncle did in 1987.

When I think of Reinforcement Learning I usually think of an agent or robot traveling through a maze, avoiding traps, collecting supplies. In each step it observes its state, tries to estimate what will be the best action to take based on all the experience it gained. The way I visualize it, in each state, the robot scans through a database, looking for all the valid actions it can take in that state, and picks the one with the best chance of being the optimal action - Q Learning is a fundamental Reinforcement Learning algorithm that works similar to this. This post is dedicated to the Q Learning algorithm. By the end of this post you will be able to write your own Q Learning agent and test it in an interactive environment.

A while ago I went to a Meetup about Reinforcement Learning (RL), I got into a conversation with some one that sat next to me. He asked me several question about the subject - What is the difference between RL and supervised/unsupervised learning? What is the difference between several types of algorithms? When would you choose this framework over another one?

Decisions are hard, they have always been. And when you finally find something you like, there is always that thought, in the back of your head - “can I find something better?”.