Reinforcement Learning Algorithms: An Overview and Classification

The desire to make applications and machines more intelligent and the to enable their operation without human interaction have been innovations in neural networks, deep learning, and other machine techniques. Although reinforcement learning has been primarily used in games, recent advancements and the development of diverse and powerful algorithms have enabled the reinforcement learning community to from playing video games to solving complex real-life problems in systems such as self-driving cars, delivery drones, and automated. Understanding the environment of an application and the algorithms' plays a vital role in selecting the appropriate reinforcement algorithm that successfully solves the problem on hand in an efficient. Consequently, in this study, we identify three main environment types classify reinforcement learning algorithms according to those environment. Moreover, within each category, we identify relationships between. The overview of each algorithm provides insight into the' foundations and reviews similarities and differences among. This study provides a perspective on the field and helps and researchers to select the appropriate algorithm for their use.