Getting Started with Machine Learning Basics: Supervised, Unsupervised and Reinforcement Learning

Source: Deep Learning on Medium

Reinforcement Learning

Reinforcement learning is one of three basic machine learning paradigms, alongside supervised learning and unsupervised learning. It is a type of machine learning algorithm that allows an agent to decide the best next action based on its current state by learning behaviors.

To get the machine to do what the programmer wants, artificial intelligence gets either rewards or penalties for the actions it performs. The agent is rewarded or penalized with a point for a correct or a wrong answer, and based on the positive reward points gained the model trains itself. And again once trained it gets ready to predict the new data presented to it. Its goal is to maximize the total reward.

Reinforcement algorithms usually learn about their actions through the hit and trial method. Imagine, for example, a video game in which the player needs to move to certain places at certain times to earn points, In this situations a reinforcement algorithm playing that game would start by moving randomly but, over time through hit and trail, it would learn where and when it needed to move the in-game character to maximize its point total. In reinforcement learning, artificial intelligence faces a game-like situation.

Reinforcement learning is all about making decisions sequentially. In simple words, we can say that the out depends on the state of the current input and the next input depends on the output of the previous input. In Reinforcement learning decision is dependent, So we give labels to sequences of dependent decisions.

The initial state from which the model will start in considered as its input and there is much possible output as there is a variety of solutions to a particular problem. Then comes to the training, it is based upon the input, the model will return a state and the user will decide to reward or punish the model based on its output. The model keeps continues to learn and once training is completed the best solution is decided based on the maximum reward.


  • Reinforcement Learning can be used for industrial automation in the robotics industry.
  • Reinforcement Learning can be used in machine learning, computer vision, and data processing tasks.
  • Reinforcement Learning can be used to create training systems that provide custom instruction and materials according to the requirement of the user.
  • In autonomous vehicles, we need to put safety first, minimize ride time, reduce pollution, offer passengers comfort and obey the rules of law. With an autonomous race car, on the other hand, we would emphasize speed much more than the driver’s comfort.

Although machine learning is seen as a monolith, this cutting-edge technology is diversified, with various sub-types including machine learning, deep learning, and the state-of-art technology of deep reinforcement learning.

Some of the algorithms of Reinforcement Learning include Q-Learning which is an off-policy, model-free Reinforcement Learning algorithm based on the well-known Bellman Equation. DQN is Q-learning with Neural Networks is also one of the most popular Reinforcement Learning algorithms.

After understanding the above fundamentals, one can start by using these ML techniques in various applications such as Finance, Economics, Deep learning, marketing and lots more. The key is to never stop learning and improving yourself.


Deep learning with Keras in Python

CNN for image Processing in Python

Fundamentals of AI

Analyzing IoT data in Python

NLP in Python

Text Mining in R

Marketing Analytics in R

Building Web applications in R using ShinyR

Recently I started some Financial analytics courses in R which are amazing.

Financial Trading in R

Bond Valuation and Analysis in R

Valuation of Life Insurance Products in R

Also if you are short of Project ideas to develop some skills and apply your skills DataCamp has their amazing Projects. I personally just love doing these and are my favorite. They are so fun.

DataCamp Projects

I hope you guys liked the article and learned some basics of machine learning. Make sure to like it and share it with your peers and friends.

I would also like to thank Mrinal Walia who has helped me a lot to understand and learn the basics of ML and deep learning. You can follow him and reach out to him below :

Github :

Linked In: