Computer Science – Artificial Intelligence
Scientific paper
2007-01-20
In Artificial General Intelligence, Springer (2007) 227-290
Computer Science
Artificial Intelligence
70 pages
Scientific paper
Sequential decision theory formally solves the problem of rational agents in uncertain worlds if the true environmental prior probability distribution is known. Solomonoff's theory of universal induction formally solves the problem of sequence prediction for unknown prior distribution. We combine both ideas and get a parameter-free theory of universal Artificial Intelligence. We give strong arguments that the resulting AIXI model is the most intelligent unbiased agent possible. We outline how the AIXI model can formally solve a number of problem classes, including sequence prediction, strategic games, function minimization, reinforcement and supervised learning. The major drawback of the AIXI model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIXItl that is still effectively more intelligent than any other time t and length l bounded agent. The computation time of AIXItl is of the order t x 2^l. The discussion includes formal definitions of intelligence order relations, the horizon problem and relations of the AIXI theory to other AI approaches.
No associations
LandOfFree
Universal Algorithmic Intelligence: A mathematical top->down approach 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 Universal Algorithmic Intelligence: A mathematical top->down approach, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Universal Algorithmic Intelligence: A mathematical top->down approach will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-651632