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

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.

[1]  Ray J. Solomonoff,et al.  A Formal Theory of Inductive Inference. Part II , 1964, Inf. Control..

[2]  A. Kolmogorov Three approaches to the quantitative definition of information , 1968 .

[3]  G. Chaitin A Theory of Program Size Formally Identical to Information Theory , 1975, JACM.

[4]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Vol. II , 1976 .

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

[6]  Leonid A. Levin,et al.  Randomness Conservation Inequalities; Information and Independence in Mathematical Theories , 1984, Inf. Control..

[7]  Paul M. B. Vitányi,et al.  A Theory of Learning Simple Concepts Under Simple Distributions , 1989, COLT 1989.

[8]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 1997, Texts in Computer Science.

[9]  Ming Li,et al.  Inductive Reasoning and Kolmogorov Complexity , 1992, J. Comput. Syst. Sci..

[10]  Neri Merhav,et al.  Universal prediction of individual sequences , 1992, IEEE Trans. Inf. Theory.

[11]  Roger Penrose,et al.  Shadows of the mind - a search for the missing science of consciousness , 1994 .

[12]  R. Penrose,et al.  Shadows of the Mind , 1994 .

[13]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[14]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[15]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[16]  K. Upton,et al.  A modern approach , 1995 .

[17]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[18]  John N. Tsitsiklis,et al.  Neuro-Dynamic Programming , 1996, Encyclopedia of Machine Learning.

[19]  Corso Elvezia,et al.  Discovering Neural Nets with Low Kolmogorov Complexity and High Generalization Capability , 1997 .

[20]  William I. Gasarch,et al.  Book Review: An introduction to Kolmogorov Complexity and its Applications Second Edition, 1997 by Ming Li and Paul Vitanyi (Springer (Graduate Text Series)) , 1997, SIGACT News.

[21]  William G. Faris Shadows of the Mind: A Search for the Missing Science of Consciousness , 1997 .

[22]  Jorma Rissanen,et al.  Stochastic Complexity in Statistical Inquiry , 1989, World Scientific Series in Computer Science.

[23]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[24]  Stuart J. Russell,et al.  Artificial Intelligence , 1999 .

[25]  Marcus Hutter,et al.  A Theory of Universal Artificial Intelligence based on Algorithmic Complexity , 2000, ArXiv.

[26]  Kindler-Rohrborn,et al.  In press , 1994, Molecular carcinogenesis.

[27]  Marcus Hutter New Error Bounds for Solomonoff Prediction , 2001, J. Comput. Syst. Sci..

[28]  Marcus Hutter General Loss Bounds for Universal Sequence Prediction , 2001, ICML.