Reinforcement learning compared to unsupervised learning

Introduction

Laymen explanation

Reinforcement learning is done without any supervision. Then what makes it to be different than Unsupervised learning? Both uses unlabelled data.

If you are interested to know this, then this document helps.

Technical explanation

Reinforcement learning is neither based on supervised learning nor unsupervised learning. Moreover, here the algorithms learn to react to an environment on their own. It is rapidly growing and moreover producing a variety of learning algorithms. These algorithms are useful in the field of Robotics, Gaming etc.

RL Learning uniqueness

• In Reinforcement Learning, ML model collects data from environment itself

• The data scientist doesn't provide any training data to the RL model. Rather (s)he puts RL model to the environment

• RL aims to identify series of action based on environment input.

Comparison

Reference

https://www.aitude.com/supervised-vs-unsupervised-vs-reinforcement/

https://images.app.goo.gl/yr3eVoP7GNAkxkGW9