## Discount Factor in Reinforcement Learning

This article shows two key visual intuitions behind the usage of a discount factor in reinforcement learning with image, code, and video. Introduction Most of the advances in science and technology happened in the last 100 years. We can see mind-boggling progress in automotive, medicine, communication, energy, etc. . Among these advances, some technologies shake …

## Expected Value

In summertime when I go out, I don’t take the raincoat with me. On what basis am I not expecting it to rain during summer?. Isn’t it my past experience gives me that knowledge and estimate the outcome?. The expected value in probability theory leverages such a pattern in data to make a good representation …

## Tensors, Simple yet Complicated!!

Throughout my academics when I come across the term tensor, my brain send reflex that “something complicated, take a break, relax and read later”. Often, I gave a thought, Am I reading it Tensor or Terror!! Physicists use Tensors to describe properties of systems which vary with direction called anisotropic systems whereas for mathematicians Tensors …

## Four types of Bootstrapping

I am sure you might have heard the term bootstrapping already. The first time I heard it, I felt it like jargon. Later I came to know that there are four different scenarios the term comes in. All of them have some basic roots but are in different subject domains. The term “bootstrap” has different …

## LaTeX Tutorial

This tutorial is on the typesetting language called LaTeX. LaTeX is useful when it comes to creating complex documents like thesis, project reports, research articles, etc. We will see the basic use-cases in around 22 examples. LaTeX Installation Instructions Windows In Windows, you need to install two programs called MiKTeX and TeXstudio. Please be careful to install …

## A Short Intuitive Explanation of Vectors

What is a vector? I know you might be already thinking- “a vector is something which has magnitude and direction”. But that’s old school definition. I also used to think that way, but after I left the academic world, I had to dig deeper. The more I explored, the deeper the concept became. This post …

## Iterative Policy Improvement

Introduction Iterative Policy Improvement (IPI) is an algorithm in reinforcement learning to find the optimal course of action given the enviroment conditions. This blog post explains how it is done using a simple grid world navigating example. It works by iteratively improving an initial policy using the policy evaluation and policy improvement steps. Here’s how …

## Epsilon Greedy Algorithm in Bandit Problems

Introduction Bandit problems are the simplest possible reinforcement learning scenario. Here the bandit machine can have k arms and pulling each arm leaves the user a reward. One of the arms will be giving higher rewards in the long run and moreover this pattern could be changing over a time period. Think of the scenario …

## Automated Document Generation with Python & LaTeX

Did you ever needed to do automated PDF creation using a table of information?.  Creating a Word document with certain formatting, styles, and tables would be the easy choice for a few pages of data. But what if you have data that might fill 100+ pages?. Would you do it by hand? or can we …

## Inset Plotting with Matplotlib

Here in this article, I explain how to do inset plotting using Python. Inorder to do that, we will be using Python programming language and a famous plotting library named matplotlib. Let us start with a story to understand the requirement. A use case scenario Once upon a time, there was a scientist named Sarah. …