Reinforcement learning is learning what
to do --- how to map situations to actions --- so as to maximize a
numerical reward signal. The learner is not told which actions to take,
as in most forms of machine learning, but instead must discover which
actions yield the most reward by trying them. All
reinforcement learning methods have to use learning by selection in one
form or another and this contrasts sharply with supervised learning,
where the feedback from the environment directly indicates what the
correct action should have been. -Reinforcement learning: An Introduction |
Research >