A Review of Current Perspective and Propensity in Reinforcement Learning (RL) in an Orderly Manner

Abstract

Reinforcement learning is an area of Machine Learning. The three primary types of machine learning are supervised learning, unsupervised learning, and reinforcement learning (RL). Pre-training a model on a labeled dataset is known as supervised learning. The model is trained on unlabeled data in unsupervised learning, on the other hand. Instead of being driven by labels, RL is motivated by assessing feedback. By interacting with the environment and choosing the best course of action in each circumstance in order to maximize the reward, the agent learns the best way to solve sequential decision-making issues. The RL agent chooses how to carry out tasks on its own. Furthermore, since there are no training data, the agent learns by gaining experience. In order to make subsequent judgments, RL aids agents in efficiently interacting with their surroundings. In this essay, the state-of-the-art RL is thoroughly reviewed in the literature. Applications for reinforcement learning (RL) may be found in a wide range of industries, including smart grids, robots, computer vision, healthcare, gaming, transportation, finance, and engineering.