## 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. |

### What people are saying - Write a review

We haven't found any reviews in the usual places.

### Contents

A Short Tour Through the Book | 1 |

Simplicity Uncertainty | 29 |

2 Prefix coding of natural numbers and strings | 34 |

14 Kolmogorovs axioms of probability theory | 42 |

25 Posterior convergence of M to i | 48 |

31 MartinL6f random sequences | 54 |

Universal Sequence Prediction | 65 |

8 Convergence of random sequences | 71 |

1 The agent model | 126 |

The Universal Algorithmic Agent AIXI | 141 |

12 We expect AIXI to be universally optimal | 146 |

30 Discounted AIp model and value | 159 |

Important Environmental Classes | 185 |

Computational Aspects | 209 |

1 The fastest algorithm | 211 |

8 Effective intelligence order relation | 226 |

### Common terms and phrases

action agent AI/i AIXI model algorithmic information theory approximable arbitrary argument assume assumption asymptotically axioms Bayes mixtures binary chain rule Chapter chronological semimeasure coding conditional probabilities constant convergence countable cycle decision theory defined definition depends deterministic discount enumerable semimeasures environment ergodic MDPs error bounds exists expected reward factor feedback finitely computable formal hence horizon i-expected implies induction inequality infinite input intelligence interpreted Kolmogorov complexity Lemma length Levin search loss bounds loss functions machine learning maximize measure minimax minimization number of errors Occam's razor optimal policy output yk Pareto optimality performance player prediction scheme predictor prior probability probabilistic probability distribution probability theory problem classes proof prove recursive reinforcement learning restricted reward sum Section self-optimizing policies sense sequence prediction sequential decision theory Solomonoff solve string supervised learning Theorem true universal prior universal Turing machine weights xi:oo zero