16.1 Agent and Environment

Reinforcement Learning (RL) is built around two pieces: an agent that makes decisions, and an environment the agent lives in. At each step the agent observes the current state of the environment, takes an action, and the environment responds with a new state and a reward signal. This loop repeats over and over.

Think of a taxi driver in Addis Ababa as the agent and the city's streets, traffic, and passengers as the environment. The driver sees the current situation (state), decides where to turn (action), and earns a fare or wastes fuel (reward) depending on the outcome.