Intelligence is a very difficult concept and, until recently, no one has succeeded in giving it a satisfactory formal definition.
Most researchers have given up grappling with the notion of intelligence in full generality, and instead focus on related but more limited concepts – but Marcus Hutter argues that mathematically defining intelligence is not only possible, but crucial to understanding and developing super-intelligent machines. From this, his research group has even successfully developed software that can learn to play computer games from scratch.
But first, how do we define "intelligence"? Hutter's group has sifted through the psychology, philosophy and artificial intelligence literature and searched for definitions individual researchers and groups came up with. The characterizations are very diverse, but there seems to be a recurrent theme which we have aggregated and distilled into the following definition: Intelligence is an agent's ability to achieve goals or succeed in a wide range of environments.
The emerging scientific field is called universal artificial intelligence, with AIXI being the resulting super-intelligent agent. AIXI has a planning component and a learning component. The goal of AIXI is to maximise its reward over its lifetime – that's the planning part.
In summary, every interaction cycle consists of observation, learning, prediction, planning, decision, action and reward, followed by the next cycle. If you're interested in exploring further, AIXI integrates numerous philosophical, computational and statistical principles:
- Ockham's razor (simplicity) principle for model selection
- Epicurus principle of multiple explanations as a justification of model averaging
- Bayes rule for updating beliefs
- Turing machines as universal description language
- Kolmogorov complexity to quantify simplicity
- Solomonoff's universal prior, and
- Bellman equations for sequential decision making.
AIXI's algorithm rigorously and uniquely defines a super-intelligent agent that learns to act optimally in arbitrary unknown environments. One can prove amazing properties of this agent – in fact, one can prove that in a certain sense AIXI is the most intelligent system possible. Note that this is a rather coarse translation and aggregation of the mathematical theorems into words, but that is the essence.
Since AIXI is incomputable, it has to be approximated in practice. In recent years, we have developed various approximations, ranging from provably optimal to practically feasible algorithms.
The point is not that AIXI is able to play these games (they are not hard) – the remarkable fact is that a single agent can learn autonomously this wide variety of environments. AIXI is given no prior knowledge about these games; it is not even told the rules of the games! It starts as a blank canvas, and just by interacting with these environments, it figures out what is going on and learns how to behave well. This is the really impressive feature of AIXI and its main difference to most other projects.
Even though IBM Deep Blue plays better chess than human Grand Masters, it was specifically designed to do so and cannot play Jeopardy. Conversely, IBM Watson beats humans in Jeopardy but cannot play chess – not even TicTacToe or Pac-Man. AIXI is not tailored to any particular application. If you interface it with any problem, it will learn to act well and indeed optimally.