Unveling Chess Algorithms Using Reinforcement Learning and Traditional Chess Approaches in AI

In the history of Artificial Intelligence, chess has been the subject of the many researches. Chess bots are now capable of beating grandmasters using reinforcement learning which is a branch of Artificial Intelligence that focuses on developing intelligent systems capable of making optimal decisions through engagement with the environment via trial-and-error. Alpha Zero, Stockfish 8, and Q-learning are the three prominent methods used in chess bots. These methods have revolutionized the field of artificial intelligence in chess, showcasing remarkable capabilities and advancements. This paper provides a comparative study of these approaches by examining the contrast in their underlying approaches, performance, training methodologies, and limitations.