Focused on decision-making, solving a particular problem where decision-making is sequential, and the goal is long-term. e.g. game-playing, robotics, resource-management, logistics.
Uses the notion of an agent that learns by taking actions in an environment, receives feedback in the form of reward or penalty generated by those actions, and adjusts its strategy(policy) to maximize cumulative rewards over time.
RL learns an optimal policy for a given (set of) behavior and environment.
Regularization