In the machine learning, a machine is made intelligent not by the specific programming but by task from the previous experience. In this machine learns automatically without human intervention. The process of learning starts with the developing the model using training of the quality data sets and algorithms. The choice of algorithms depends on what type of data do we have and what kind of task we are trying to automate.
However, generally speaking, Machine Learning Algorithms are divided into 3 types i.e. Supervised Machine Learning Algorithms, Unsupervised Machine Learning Algorithms, and Reinforcement Machine Learning Algorithms.
Reinforcement learning is a machine learning process to human beings. The reinforcement algorithm is based on learn and reward. Machine learns from own mistakes. This means that the algorithm decides its next action by learning behaviours that are based on its current state and that will maximize the reward in the future. And like humans, this works for machines as well! For example, Google’s AlphaGo computer program was able to beat the world champion in the game of Go (that’s a human!) in 2017 using Reinforcement Learning.