Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory

Simple item page
dc.creatorHutter, Marcus
dc.date2000-12-16
dc.date.accessioned2026-07-07T08:17:41Z
dc.date.available2026-07-07T08:17:41Z
dc.descriptionDecision theory formally solves the problem of rational agents in uncertain worlds if the true environmental probability distribution is known. Solomonoff's theory of universal induction formally solves the problem of sequence prediction for unknown distribution. We unify both theories and give strong arguments that the resulting universal AIXI model behaves optimal in any computable environment. The major drawback of the AIXI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIXI^tl, which is still superior to any other time t and space l bounded agent. The computation time of AIXI^tl is of the order t x 2^l.
dc.description8 two-column pages, latex2e, 1 figure, submitted to ijcai
dc.identifierhttps://arxiv.org/abs/cs/0012011
dc.identifierhttp://arxiv.org/abs/cs/0012011
dc.identifierLecture Notes in Artificial Intelligence (LNAI 2167), Proc. 12th Eurpean Conf. on Machine Learning, ECML (2001) 226--238
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/134175
dc.subjectArtificial Intelligence
dc.subjectComputational Complexity
dc.subjectInformation Theory
dc.subjectMachine Learning
dc.subjectI.2; I.2.3; I.2.6; I.2.8; F.1.3; F.2
dc.titleTowards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
dc.typetext

Files

Collections

arXiv