Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic ProbabilityPersonal motivation. The dream of creating artificial devices that reach or outperform human inteUigence is an old one. It is also one of the dreams of my youth, which have never left me. What makes this challenge so interesting? A solution would have enormous implications on our society, and there are reasons to believe that the AI problem can be solved in my expected lifetime. So, it's worth sticking to it for a lifetime, even if it takes 30 years or so to reap the benefits. The AI problem. The science of artificial intelligence (AI) may be defined as the construction of intelligent systems and their analysis. A natural definition of a system is anything that has an input and an output stream. Intelligence is more complicated. It can have many faces like creativity, solving prob lems, pattern recognition, classification, learning, induction, deduction, build ing analogies, optimization, surviving in an environment, language processing, and knowledge. A formal definition incorporating every aspect of intelligence, however, seems difficult. Most, if not all known facets of intelligence can be formulated as goal driven or, more precisely, as maximizing some utility func tion. It is, therefore, sufficient to study goal-driven AI; e. g. the (biological) goal of animals and humans is to survive and spread. The goal of AI systems should be to be useful to humans. |
Contents
2 Simplicity Uncertainty | 28 |
3 Universal Sequence Prediction | 65 |
4 Agents in Known ProbabilisticEnvironments | 125 |
5 The Universal Algorithmic Agent AIXI | 141 |
6 Important Environmental Classes | 184 |
| 209 | |
8 Discussion | 231 |
Bibliography | 250 |
| 265 | |
Other editions - View all
Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic ... Marcus Hutter No preview available - 2009 |
Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic ... Marcus Hutter No preview available - 2004 |
Common terms and phrases
agent AIg model AIXI model AIXItl algorithmic information theory Alµ model approximable arg max assume assumption asymptotically axioms Bayes mixtures binary chain rule conditional probabilities convergence countable cycle decision theory defined definition deterministic discount entropy enumerable semimeasures environment ergodic MDPS exists expected finitely computable formal hence horizon implies induction inequality infinite input intelligence Kolmogorov complexity ky ky Lemma length Levin search loss bounds loss functions machine learning maximize measure minimization Msemi Occam's razor optimal policy output yk Pareto optimality prediction scheme predictor prior probability probabilistic probability distribution probability theory problem classes proof prove random recursive reinforcement learning Section self-optimizing policies semi sense sequence prediction sequential decision theory shortest Solomonoff's solve string supervised learning Theorem true universal prior universal Turing machine w₁ weights ΑΙξ Θε ξυ