Applied Reinforcement Learning I: Q-Learning | by Javier Martínez Ojeda | Oct, 2022
Understand the Q-Learning algorithm step by step, as well as the main components of any RL-based systemPhoto by DeepMind on UnsplashWe have all experienced a situation in which we have done something wrong, been punished for it, and this has made us not to do it again. In the same way, many times good actions are rewarded, encouraging us to repeat them on more occasions. Following this parallelism, Reinforcement Learning agents will take certain actions following a strategy/policy, and receive positive or negative…