Principles of Solomonoff Induction and AIXI

We identify principles characterizing Solomonoff Induction by demands on an agent’s external behaviour. Key concepts are rationality, computability, indifference and time consistency. Furthermore, we discuss extensions to the full AI case to derive AIXI.

[1]  A. Church.  Review: A. M. Turing, On Computable Numbers, with an Application to the Entscheidungsproblem , 1937 .

[2]  B. D. Finetti.  La prévision : ses lois logiques, ses sources subjectives , 1937 .

[3]  A. Turing.  On computable numbers, with an application to the Entscheidungsproblem , 1937, Proc. London Math. Soc..

[4]  E. Rowland.  Theory of Games and Economic Behavior , 1946, Nature.

[5]  C. S. Wallace,et al.  An Information Measure for Classification , 1968, Comput. J..

[6]  Ray J. Solomonoff,et al.  Complexity-based induction systems: Comparisons and convergence theorems , 1978, IEEE Trans. Inf. Theory.

[7]  E. Kreyszig.  Introductory Functional Analysis With Applications , 1978 .

[8]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[9]  J. Diestel.  Sequences and series in Banach spaces , 1984 .

[10]  Ming Li,et al.  Kolmogorov Complexity and its Applications , 1991, Handbook of Theoretical Computer Science, Volume A: Algorithms and Complexity.

[11]  R. Sugden.  Rational Choice: A Survey of Contributions from Economics and Philosophy , 1991 .

[12]  David L. Dowe,et al.  Minimum Message Length and Kolmogorov Complexity , 1999, Comput. J..

[13]  R. Solomonoff.  A PRELIMINARY REPORT ON A GENERAL THEORY OF INDUCTIVE INFERENCE , 2001 .

[14]  Marcus Hutter.  Simulation Algorithms for Computational Systems Biology , 2017, Texts in Theoretical Computer Science. An EATCS Series.

[15]  C. S. Wallace,et al.  Statistical and Inductive Inference by Minimum Message Length (Information Science and Statistics) , 2005 .

[16]  R. Solomonoff.  Does Algorithmic Probability Solve the Problem of Induction , 2006 .

[17]  Peter Grünwald,et al.  Invited review of the book Statistical and Inductive Inference by Minimum Message Length , 2006 .

[18]  Marcus Hutter,et al.  On Universal Prediction and Bayesian Confirmation , 2007, Theor. Comput. Sci..

[19]  Jorma Rissanen,et al.  Minimum Description Length Principle , 2010, Encyclopedia of Machine Learning.

[20]  David L. Dowe,et al.  MML, hybrid Bayesian network graphical models, statistical consistency, invarianc , 2010 .

[21]  Marcus Hutter,et al.  Axioms for Rational Reinforcement Learning , 2011, ALT.

[22]  Marcus Hutter,et al.  A Philosophical Treatise of Universal Induction , 2011, Entropy.

[23]  Marcus Hutter,et al.  (Non-)Equivalence of Universal Priors , 2013, Algorithmic Probability and Friends.