Open Problems in Universal Induction & Intelligence
arXiv:0907.0746
Abstract
Specialized intelligent systems can be found everywhere: finger print, handwriting, speech, and face recognition, spam filtering, chess and other game programs, robots, et al. This decade the first presumably complete mathematical theory of artificial intelligence based on universal induction-prediction-decision-action has been proposed. This information-theoretic approach solidifies the foundations of inductive inference and artificial intelligence. Getting the foundations right usually marks a significant progress and maturing of a field. The theory provides a gold standard and guidance for researchers working on intelligent algorithms. The roots of universal induction have been laid exactly half-a-century ago and the roots of universal intelligence exactly one decade ago. So it is timely to take stock of what has been achieved and what remains to be done. Since there are already good recent surveys, I describe the state-of-the-art only in passing and refer the reader to the literature. This article concentrates on the open problems in universal induction and its extension to universal intelligence.
32 LaTeX pages
References in corpus (15)
- Decision-Theoretic Planning: Structural Assumptions and Computational Leverage
- Online Planning Algorithms for POMDPs
- Policy Iteration for Factored MDPs
- A Formal Measure of Machine Intelligence
- The Limits of Mathematics -- A course on information theory and the limits of formal reasoning
- Similarity of Objects and the Meaning of Words
- Asymptotics of Discrete MDL for Online Prediction
- Self-Optimizing and Pareto-Optimal Policies in General Environments based on Bayes-Mixtures
- MDL Convergence Speed for Bernoulli Sequences
- Universal Learning of Repeated Matrix Games
- Algorithmic Complexity Bounds on Future Prediction Errors
- Convergence and Error Bounds for Universal Prediction of Nonbinary Sequences
- Universal Sequential Decisions in Unknown Environments
- On the Foundations of Universal Sequence Prediction
- Tests of Machine Intelligence