Reinforcement learning is a method for a computer to learn how to perform a task by attempting new things and receiving rewards when it succeeds. It entails teaching an agent to make decisions in a given situation in order to maximize a reward. The agent learns through trial and error, earning positive or negative reinforcement based on its behaviors. The agent monitors the current condition of the environment and chooses an action to do at each time step. The action results in a new state and a matching reward, and the cycle continues. Reinforcement learning is used in the chess game to educate the machine each time by rewarding excellent moves and inflicting penalties for poor moves.