A High-Performance Explanation-Based Learning Algorithm

Abstract The main contribution of this paper is a new domain-independent explanation-based learning (EBL) algorithm. The new EBL∗DI algorithm significantly outperforms traditional EBL algorithms both by learning in situations where traditional algorithms cannot learn as well as by providing greater problem-solving performance improvement in general. The superiority of the EBL∗DI algorithm is demonstrated with experiments in three different application domains. The EBL∗DI algorithm is developed using a novel formal framework in which traditional EBL techniques are reconstructed as the structured application of three explanation-transformation operators. We extend this basic framework by introducing two additional operators that, when combined with the first three operators, allow us to prove a completeness result: in the formal framework, every EBL algorithm is equivalent to the application of the five transformation operators according to some control strategy. The EBL∗DI algorithm employs all five proof-transformation operators guided by five domain-independent control heuristics.

[1]  Raymond J. Mooney,et al.  The Effect of Rule Use on the Utility of Explanation-Based Learning , 1989, IJCAI.

[2]  Haym Hirsh,et al.  Reasoning about Operationality for Explanation-Based Learning , 1988, ML.

[3]  Allen Newell,et al.  Some Chunks Are Expensive , 1988, ML.

[4]  Richard E. Korf,et al.  Depth-First Iterative-Deepening: An Optimal Admissible Tree Search , 1985, Artif. Intell..

[5]  Alberto Maria Segre.  On the Operationality/Generality Trade-off in Explanation-based Learning , 1987, IJCAI.

[6]  Charles Elkan,et al.  Automated Inductive Reasoning about Logic Programs , 1988, ICLP/SLP.

[7]  Thomas G. Dietterich.  Learning at the knowledge level , 2004, Machine Learning.

[8]  Richard M. Keller,et al.  Defining Operationality for Explanation-Based Learning , 1987, Artificial Intelligence.

[9]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[10]  Stuart J. Russell,et al.  A Logical Approach to Reasoning by Analogy , 1987, IJCAI.

[11]  Alberto Maria Segre.  Learning how to plan , 1991, Robotics Auton. Syst..

[12]  Allen Newell,et al.  Empirical explorations with the logic theory machine: a case study in heuristics , 1995 .

[13]  Charles Elkan,et al.  Conspiracy Numbers and Caching for Searching And/Or Trees and Theorem-Proving , 1989, IJCAI.

[14]  Stuart J. Russell,et al.  Boundaries of Operationality , 1988, ML.

[15]  C. Cordell Green,et al.  Application of Theorem Proving to Problem Solving , 1969, IJCAI.

[16]  Alberta Maria Segre,et al.  Machine Learning of Robot Assembly Plans , 1988 .

[17]  William W. Cohen.  Learning Approximate Control Rules of High Utility , 1990, ML.

[18]  Michael J. Pazzani,et al.  Explanation-based learning of diagnostic heuristics: a comparison of learning from success and failure , 1989, [1989] Proceedings. The Annual AI Systems in Government Conference.

[19]  Alberto Maria Segre.  On Combining Multiple Speedup Techniques , 1992, ML.

[20]  Alan Bundy,et al.  Explanation-Based Generalisation = Partial Evaluation , 1988, Artif. Intell..

[21]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[22]  Alberto M. Segre,et al.  Not the Last Word on EBL Algorithms , 1989 .

[23]  Sridhar Mahadevan.  Using Determinations in EBL: A Solution to the incomplete Theory Problem , 1989, ML.

[24]  Steven Minton,et al.  Quantitative Results Concerning the Utility of Explanation-based Learning , 1988, Artif. Intell..

[25]  Matthew L. Ginsberg,et al.  Iterative Broadening , 1990, Artif. Intell..

[26]  Devika Subramanian,et al.  The Utility of EBL in Recursive Domain Theories , 1990, AAAI.

[27]  Gerald J. Sussman,et al.  A Computational Model of Skill Acquisition , 1973 .

[28]  Keith L. Clark,et al.  Negation as Failure , 1987, Logic and Data Bases.

[29]  Raymond Reiter.  On Closed World Data Bases , 1977, Logic and Data Bases.

[30]  Scott Bennett,et al.  A Domain Independent Explanation-Based Generalizer , 1986, AAAI.

[31]  Jack Mostow.  Searching for Operational Concept Descriptions in BAR, MetaLEX, and EBG , 1987 .

[32]  Stuart J. Russell,et al.  IMEX: Overcoming Intactability In Explanation Based Learning , 1988, AAAI.

[33]  Jack Mostow,et al.  A Problem-Solver for Making Advice Operational , 1983, AAAI.

[34]  Claudio Carpineto.  Combining EBL from Success and EBL from Failure with Parameter Version Spaces , 1990, ECAI.

[35]  Haym Hirsh,et al.  Explanation-based Generalization in a Logic-Programming Environment , 1987, IJCAI.