A Theory of Universal Artificial Intelligence based on Algorithmic Complexity

Abstract

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 parameterless theory of universal Artificial Intelligence. We give strong arguments that the resulting AIXI 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 AIXI model can formally solve them. 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 effectively more intelligent than any other time t and space l bounded agent. The computation time of AIXI-tl is of the order tx2^l. Other discussed topics are formal definitions of intelligence order relations, the horizon problem and relations of the AIXI theory to other AI approaches.

62 pages, LaTeX

Cited by in corpus (11)

• AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
• Algorithmic Theories of Everything
• AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence
• General Loss Bounds for Universal Sequence Prediction
• Friendly Artificial Intelligence: the Physics Challenge
• Intelligence, physics and information -- the tradeoff between accuracy and simplicity in machine learning
• A Gentle Introduction to Quantum Computing Algorithms with Applications to Universal Prediction
• On the Computability of AIXI
• Universal Policies for Software-Defined MDPs
• An effective Procedure for Speeding up Algorithms
• Turing-Universal Learners with Optimal Scaling Laws