Artificial Scientists & Artists Based on the Formal Theory of Creativity

I have argued that a simple but general formal theory of creativity explains many essential aspects of intelligence including science, art, music, humor. It is based on the concept of maximizing reward for the creation or discovery of novel patterns allowing for improved data compression or prediction. Here I discuss what kind of general bias towards algorithmic regularities we insert into our robots by implementing the principle, why that bias is good, and how the approach greatly generalizes the field of active learning. I emphasize the importance of limited computational resources for online prediction and compression, and provide discrete and continuous time formulations for ongoing work on building an Artificial General Intelligence (AGI) based on variants of the artificial creativity framework.

[1]  Tom Schaul,et al.  Fitness Expectation Maximization , 2008, PPSN.

[2]  S. Hochreiter,et al.  REINFORCEMENT DRIVEN INFORMATION ACQUISITION IN NONDETERMINISTIC ENVIRONMENTS , 1995 .

[3]  Jürgen Schmidhuber,et al.  Curious model-building control systems , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[4]  Jürgen Schmidhuber,et al.  Developmental robotics, optimal artificial curiosity, creativity, music, and the fine arts , 2006, Connect. Sci..

[5]  Jürgen Schmidhuber,et al.  State-Dependent Exploration for Policy Gradient Methods , 2008, ECML/PKDD.

[6]  Jürgen Schmidhuber,et al.  A possibility for implementing curiosity and boredom in model-building neural controllers , 1991 .

[7]  David A. Huffman,et al.  A method for the construction of minimum-redundancy codes , 1952, Proceedings of the IRE.

[8]  Jürgen Schmidhuber,et al.  Gödel Machines: Fully Self-referential Optimal Universal Self-improvers , 2007, Artificial General Intelligence.

[9]  SolomonoffR..  Complexity-based induction systems , 2006 .

[10]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[12]  Marcus Hutter,et al.  Universal Artificial Intelligence: Sequential Decisions Based on Algorithmic Probability (Texts in Theoretical Computer Science. An EATCS Series) , 2006 .

[13]  Frank Sehnke,et al.  Policy Gradients with Parameter-Based Exploration for Control , 2008, ICANN.

[14]  Risto Miikkulainen,et al.  Efficient Non-linear Control Through Neuroevolution , 2006, ECML.

[15]  J. Schmidhuber.  What''s interesting? , 1997 .

[16]  Jürgen Schmidhuber,et al.  Low-Complexity Art , 2017 .

[17]  Jürgen Schmidhuber,et al.  Completely Self-referential Optimal Reinforcement Learners , 2005, ICANN.

[18]  Jürgen Schmidhuber,et al.  Hierarchies of Generalized Kolmogorov Complexities and Nonenumerable Universal Measures Computable in the Limit , 2002, Int. J. Found. Comput. Sci..

[19]  Jürgen Schmidhuber,et al.  Simple algorithmic theory of subjective beauty, novelty, surprise, interestingness, attention, curiosity, creativity, art, science, music, jokes (特集 高次機能の学習と創発--脳・ロボット・人間研究における新たな展開) , 2009 .

[20]  Jürgen Schmidhuber,et al.  Policy Gradient Critics , 2007, ECML.

[21]  Ming Li,et al.  An Introduction to Kolmogorov Complexity and Its Applications , 2019, Texts in Computer Science.

[22]  W. J. Studden,et al.  Theory Of Optimal Experiments , 1972 .

[23]  Jürgen Schmidhuber,et al.  Exploring the predictable , 2003 .

[24]  W. Vent,et al.  Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .

[25]  Tom Schaul,et al.  Natural Evolution Strategies , 2008, 2008 IEEE Congress on Evolutionary Computation (IEEE World Congress on Computational Intelligence).

[26]  J. Schmidhuber.  Science as By-Products of Search for Novel Patterns , or Data Compressible in Unknown Yet Learnable Ways , 2009 .

[27]  Jürgen Schmidhuber,et al.  Ultimate Cognition à la Gödel , 2009, Cognitive Computation.

[28]  Jürgen Schmidhuber,et al.  The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions , 2002, COLT.

[29]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[30]  Jürgen Schmidhuber,et al.  Sequential neural text compression , 1996, IEEE Trans. Neural Networks.

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

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

[33]  Ingo Rechenberg,et al.  Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[34]  Yishay Mansour,et al.  Policy Gradient Methods for Reinforcement Learning with Function Approximation , 1999, NIPS.

[35]  Jürgen Schmidhuber,et al.  Driven by Compression Progress: A Simple Principle Explains Essential Aspects of Subjective Beauty, Novelty, Surprise, Interestingness, Attention, Curiosity, Creativity, Art, Science, Music, Jokes , 2008, ABiALS.

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

[37]  Jürgen Schmidhuber,et al.  Simple Algorithmic Principles of Discovery, Subjective Beauty, Selective Attention, Curiosity & Creativity , 2007, Discovery Science.

[38]  Jürgen Schmidhuber,et al.  Optimal Ordered Problem Solver , 2002, Machine Learning.

[39]  Martin V. Butz,et al.  Anticipatory Behavior in Adaptive Learning Systems, From Brains to Individual and Social Behavior [the book is a result from the third workshop on anticipatory behavior in adaptive learning systems, ABiALS 2006, Rome, Italy, September 30, 2006, colocated with SAB 2006] , 2007, ABiALS book.