On learning to coordinate: random bits help, insightful normal forms, and competency isomorphisms

A mere bounded number of random bits judiciously employed by a probabilistically correct algorithmic coordinator is shown to increase the power of learning to coordinate compared to deterministic algorithmic coordinators. Furthermore, these probabilistic algorithmic coordinators are provably not characterized in power by teams of deterministic ones. An insightful, enumeration technique based, normal form characterization of the classes that are learnable by total computable coordinators is given. These normal forms are for insight only since it is shown that the complexity of the normal form of a total computable coordinator can be infeasible compared to the original coordinator. Montagna and Osherson showed that the competence class of a total coordinator cannot be strictly improved by another total coordinator. It is shown in the present paper that the competencies of any two total coordinators are the same modulo isomorphism. Furthermore, a completely effective, index set version of this competency isomorphism result is given, where all the coordinators are total computable. We also investigate the competence classes of total coordinators from the points of view of topology and descriptive set theory.

[1]  Y. Ershov.  A hierarchy of sets. I , 1968 .

[2]  Stuart A. Kurtz,et al.  On the role of search for learning from examples , 2001, J. Exp. Theor. Artif. Intell..

[3]  D. C. Cooper,et al.  Theory of Recursive Functions and Effective Computability , 1969, The Mathematical Gazette.

[4]  Martin Kummer,et al.  Learning branches and learning to win closed games , 1996, COLT '96.

[5]  Jr. Hartley Rogers.  Theory of Recursive Functions and Effective Computability , 1969 .

[6]  E. Mark Gold,et al.  Language Identification in the Limit , 1967, Inf. Control..

[7]  Sanjay Jain,et al.  Open Problems in "Systems That Learn" , 1994, J. Comput. Syst. Sci..

[8]  J. M. Barzdin,et al.  Prognostication of Automata and Functions , 1971, IFIP Congress.

[9]  G. Reeke.  The society of mind , 1991 .

[10]  R. Soare.  Recursively enumerable sets and degrees , 1987 .

[11]  Daniel N. Osherson,et al.  Systems That Learn: An Introduction to Learning Theory for Cognitive and Computer Scientists , 1990 .

[12]  John Case,et al.  Predictive Learning Models for Concept Drift , 1998, ALT.

[13]  Leonard Pitt,et al.  A Characterization of Probabilistic Inference , 1984, FOCS.

[14]  Franco Montagna,et al.  Learning to Coordinate; a Recursion Theoretic Perspective , 2004, Synthese.

[15]  Carl H. Smith,et al.  On the impact of forgetting on learning machines , 1995, JACM.

[16]  John Case,et al.  Learning to Win Process-Control Games Watching Game-Masters , 1998, Inf. Comput..

[17]  Manuel Blum,et al.  Toward a Mathematical Theory of Inductive Inference , 1975, Inf. Control..

[18]  Carl H. Smith,et al.  Probability and Plurality for Aggregations of Learning Machines , 1987, Inf. Comput..

[19]  John Case,et al.  Incremental Concept Learning for Bounded Data Mining , 1997, Inf. Comput..

[20]  Leonard Pitt,et al.  Probabilistic inductive inference , 1989, JACM.