Vol. 9, Special Issue 4, Part D (2023)

Abstract
In today's world where everything is related to AI (Artificial Intelligence), more focus is put on machine learning. In the hierarchy of AI, it consists of deep learning and further covers ML. So, maybe we can say that machine learning is a sub-part of artificial intelligence, which is basically defined as the scientific study of algorithms that help programs improve themselves. In the normal world, learning is led by whether there is a supervisor to teach or without a supervisor by assuming. There is also another way in which anyone can learn by experience by counting good and bad experiences. But machine learning uses all types of learning, such as supervised, unsupervised and reinforcement learning. According to reinforcement learning, an agent placed in an environment must learn how to behave successfully in that environment. In this paper, we introduce the concept of reinforcement learning and how it plays a crucial role in machine learning and what are the major advantages of reinforcement learning in the field of machine learning.