Q-learning is a type of model-free reinforcement learning algorithm used in the context of Markov Decision Processes (MDPs). It allows an agent to learn how to optimally make decisions by interacting with an environment to maximize a cumulative reward. Here's a breakdown of the key concepts involved in Q-learning: 1. **Agent and Environment**: In Q-learning, an agent interacts with an environment by performing actions and receiving feedback in the form of rewards.
New to topics? Read the docs here!