Towards a Universal Theory of Artificial Intelligence Based on Algorithmic Probability and Sequential Decisions

Authors:
Marcus Hutter
Affiliations:
-
Venue:
EMCL '01 Proceedings of the 12th European Conference on Machine Learning
Year:
2001

Citing 14
Cited 2

Artificial intelligence: a modern approach

Artificial intelligence: a modern approach
An introduction to Kolmogorov complexity and its applications (2nd ed.)

An introduction to Kolmogorov complexity and its applications (2nd ed.)
Shifting Inductive Bias with Success-Story Algorithm, AdaptiveLevin Search, and Incremental Self-Improvement

Machine Learning - Special issue on inductive transfer
Discovering neural nets with low Kolmogorov complexity and high generalization capability

Neural Networks
A Theory of Program Size Formally Identical to Information Theory

Journal of the ACM (JACM)
New error bounds for Solomonoff prediction

Journal of Computer and System Sciences
Dynamic Programming and Optimal Control, Two Volume Set

Dynamic Programming and Optimal Control, Two Volume Set
Stochastic Complexity in Statistical Inquiry Theory

Stochastic Complexity in Statistical Inquiry Theory
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Neuro-Dynamic Programming

Neuro-Dynamic Programming
Dynamic Programming

Dynamic Programming
General Loss Bounds for Universal Sequence Prediction

General Loss Bounds for Universal Sequence Prediction
Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory

Towards a Universal Theory of Artificial Intelligence based on Algorithmic Probability and Sequential Decision Theory
Reinforcement learning: a survey

Journal of Artificial Intelligence Research

The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions

COLT '02 Proceedings of the 15th Annual Conference on Computational Learning Theory
Defensive universal learning with experts

ALT'05 Proceedings of the 16th international conference on Algorithmic Learning Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

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 distributions. We unify both theories and give strong arguments that the resulting universal AIξ model behaves optimally in any computable environment. The major drawback of the AIξ model is that it is uncomputable. To overcome this problem, we construct a modified algorithm AIξtl, which is still superior to any other time t and length l bounded agent. The computation time of AIξtl is of the order tċ2l.