The Role of the Critic in Learning Systems

Buchanan, Mitchell, Smith, and Johnson (1978) described a general model of learning systems that included a component called the Critic. The task of the Critic was described as threefold: evaluation of the past actions of the performance element of the learning system, localization of credit and blame to particular portions of that performance element, and recommendation of possible improvements and modifications in the performance element. This article analyzes these three tasks in detail and surveys the methods that have been employed in existing learning systems to accomplish them. The principle method used to evaluate the performance element is to develop a global performance standard by (a) consulting an external source of knowledge, (b) consulting an internal source of knowledge, or (c) conducting deep search. Credit and blame have been localized by (a) asking an external knowledge source to do the localization, (b) factoring the global performance standard to produce a local performance standard, and (c) conducting controlled experiments on the performance element. Recommendations have been conmiunicated to the learning element using (a) local training instances, (b) correlation coefficients, and (c) partially-instantiated schemata.

[1]  E. Feigenbaum,et al.  Computers and Thought , 1963 .

[2]  A. L. Samuel,et al.  Some studies in machine learning using the game of checkers. II: recent progress , 1967 .

[3]  Patrick Henry Winston,et al.  Learning structural descriptions from examples , 1970 .

[4]  Donald A. Waterman,et al.  Generalization Learning Techniques for Automating the Learning of Heuristics , 1970, Artif. Intell..

[5]  Richard Fikes,et al.  Learning and Executing Generalized Robot Plans , 1993, Artif. Intell..

[6]  Jack Belzer,et al.  Encyclopedia of Computer Science and Technology , 2020 .

[7]  Gerald Jay Sussman,et al.  A Computer Model of Skill Acquisition , 1975 .

[8]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .

[9]  Tom Michael Mitchell,et al.  Model-directed learning of production rules , 1977, SGAR.

[10]  田中 穂積 E.H.Shortliffe 著, "Computer-Based Medical Consultations : MYCIN", American Elsevier, A4判, 264ぺージ, \10,080, 1976 , 1978 .

[11]  Frederick Hayes-Roth,et al.  An interference matching technique for inducing abstractions , 1978, CACM.

[12]  Ryszard S. Michalski,et al.  Pattern Recognition as Knowledge-Guided Computer Induction , 1978 .

[13]  Tom Michael Mitchell Version spaces: an approach to concept learning. , 1979 .

[14]  Tom M. Mitchell,et al.  Models of Learning Systems. , 1979 .

[15]  Tom M. Mitchell,et al.  Learning Problem-Solving Heuristics Through Practice , 1981, IJCAI.

[16]  Donald A. Waterman,et al.  Pattern-Directed Inference Systems , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Clifford R. Hollander,et al.  DART: An Expert System for Computer Fault Diagnosis , 1981, IJCAI.

[18]  Barr and Feigenbaum Edward A. Avron The Handbook of Artificial Intelligence , 1981 .