Computer Science – Artificial Intelligence
Scientific paper
2000-12-16
Lecture Notes in Artificial Intelligence (LNAI 2167), Proc. 12th Eurpean Conf. on Machine Learning, ECML (2001) 226--238
Computer Science
Artificial Intelligence
8 two-column pages, latex2e, 1 figure, submitted to ijcai
Scientific paper
Decision 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.
No associations
LandOfFree
Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-296492