Rule-Based System Against Reinforcement Learning*

Reinforcement Learning is becoming an increasingly popular type of machine learning. In it, artificial intelligence learns what the best action in each given situation is and over time optimizes the decisions it makes. On the other hand, provided that sufficiently good rules are created, a Rule-Based System is a program task that can support very complex behavior. The aim of the authors in this study is to analyze and compare the behavior of two agents, realized on the basis of these two approaches.