Universal optimal learning agents are theoretical agents designed to learn about an initially unknown environment and choose actions to maximize expected reward across a broad class of possible environments, using a universal probability model to guide their predictions and decisions. In this framework, AIXI is a formal idealization of such an agent, rather than a generally computable practical system.
A fundamental problem in artificial intelligence is that nobody really knows what intelligence is. The problem is especially acute when we need to consider artificial systems which are significantly different to humans. In this paper we approach this problem in the following way: We take a number of well known informal definitions of human intelligence that have been given by experts, and extract their essential features. These are then mathematically formalised to produce a general measure of intelligence for arbitrary machines. We believe that this equation formally captures the concept of machine intelligence in the broadest reasonable sense. We then show how this formal definition is related to the theory of universal optimal learning agents. Finally, we survey the many other tests and definitions of intelligence that have been proposed for machines.
