This chapter provides a comprehensive overview of various reinforcement learning (RL) algorithms, categorizing them based on their approach to learning and decision-making. We explore value-based methods, policy-based techniques, and hybrid approaches like actor-critic algorithms. Readers will gain insights into the strengths and applications of each algorithm type, from classic Q-learning to advanced policy gradient methods. By understanding these different approaches, readers will be better equipped to choose the most suitable algorithm for specific RL problems.