Reinforcement Learning

A method of training algorithms to make suitable actions by maximizing rewarded behavior over the course of its actions. This type of learning can take place in simulated environments, such as game-playing, which reduces the need for real-world data.

Reinforcement learning (RL) is a subset of machine learning that allows an artificial system (sometimes referred to as an agent) in a given environment to optimize its behaviour. Agents learn from feedback signals received as a result of their actions, such as rewards or punishments, with the aim of maximizing the received reward. Such signals are computed based on a given reward function, which constitutes an abstract representation of the system's goal. The goal could be, for example, to earn a high video game score or to minimize idle worker time in a factory