Curious AI is the simulation of the human capacity for curiosity in artificial intelligence. Curious AI is also known by a variety of other names including artificial curiosity, AI curiosity, curious algorithm and algorithmic curiosity.
Curiosity is what drives most self-directed learning in humans. When we detect a gap in our knowledge, our interest may be sparked, creating a desire to seek out the missing information. Emulating the behavior of a curious human in an algorithm could greatly enhance the potential for self-directed machine learning, so that an AI system would be driven to seek out or develop solutions to unfamiliar problems. That capacity is an essential component of strong or general-purpose AI, which more closely replicates human intelligence than the current narrow AI systems.
Narrow AI systems, also known as weak AI, are often capable of outperforming humans at their particular tasks. ROSS, an expert system sometimes referred to as an AI lawyer, can take over many tasks of a human legal assistant, many of them at a level far beyond what a human is capable of. ROSS can mine data from about a billion text documents, for example, analyze the information and provide precise responses to complicated questions in less than three seconds.
Narrow AI systems are limited, however, by the fact that they require specific instructions and lack the human capacity to develop approaches when faced with novel problems, which tend to stop them in their tracks. Curiosity can help AI systems behave more like humans in new situations by incorporating behaviors associated with curiosity into algorithmic models. A curious AI system might, for example, prioritize exploration by reinforcing behavior that yielded new information about its environment. Behaviors supporting the ability to explore can be reinforced and those that prevent or limit exploration can be punished.