paper
referenced-only
2000
paper:m-a-theory-of-universal-artificial-intelli-2000

A theory of universal artificial intelligence based on algorithmic complexity

ByHutter M
Original abstract (expand)

Decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomono’s theory of universal induction formally solves the problem of sequence prediction for unknown prior distribution. We combine both ideas and get a parameterless theory of universal Artificial Intelligence. We give strong arguments that the resulting AI model is the most intelligent unbiased agent possible. We outline for a number of problem classes, including sequence prediction, strategic games, function minimization, reinforcement and supervised learning, how the AI model can formally solve them. The major drawback of the AI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AI tl , which is still eectively more intelligent than any other time t and space l bounded agent. The computation time of AI tl is of the order t·2 l . Other discussed topics are formal definitions of intelligence order relations, the horizon problem and relations of the AI theory to other AI approaches.

Related work— refs + corpus + external arXiv

Cited / in-corpus / arXiv badges show which signals surfaced each row. Multi-source rows weighted higher.

Similar preprints — Semantic Scholar