Intrinsic motivation is a learning or decision-making signal that encourages an agent to act for internally generated reasons, such as curiosity, novelty, exploration, or competence. In reinforcement learning, it can help agents explore environments beyond immediate external rewards.
An intelligent agent is intrinsically motivated to act if the information content alone, of the experience resulting from the action, is the motivating factor. Information content in this context is measured in the information theory sense as quantifying uncertainty. A typical intrinsic motivation is to search for unusual (surprising) situations, in contrast to a typical extrinsic motivation such as the search for food. Intrinsically motivated artificial agents display behaviours akin to exploration and curiosity.