COMPOSER: A Probabilistic Solution to the Utility Problem in Speed-Up Learning

In machine learning there is considerable interest in techniques which improve planning ability. Initial investigations have identified a wide variety of techniques to address this issue. Progress has been hampered by the utility problem, a basic tradeoff between the benefit of learned knowledge and the cost to locate and apply relevant knowledge. In this paper we describe the COMPOSER system which embodies a probabilistic solution to the utility problem. We outline the statistical foundations of our approach and compare it against four other approaches which appear in the literature.

[1]  A. Nádas.  An Extension of a Theorem of Chow and Robbins on Sequential Confidence Intervals for the Mean , 1969 .

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

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

[4]  Steven Minton,et al.  Selectively Generalizing Plans for Problem-Solving , 1985, IJCAI.

[5]  M. Woodroofe.  Nonlinear Renewal Theory in Sequential Analysis , 1987 .

[6]  Mark S. Boddy,et al.  An Analysis of Time-Dependent Planning , 1988, AAAI.

[7]  Jaime G. Carbonell,et al.  Learning effective search control knowledge: an explanation-based approach , 1988 .

[8]  Mark Drummond,et al.  Situated Control Rules , 1989, KR.

[9]  Shaul Markovitch,et al.  Utilization Filtering: A Method for Reducing the Inherent Harmfulness of Deductively Learned Knowledge , 1989, IJCAI.

[10]  Oren Etzioni,et al.  Why PRODIGY/EBL Works , 1990, AAAI.

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

[12]  Stanley Letovsky,et al.  Operationality Criteria for Recursive Predicates , 1990, AAAI.

[13]  Gerald DeJong,et al.  A Hybrid Approach to Guaranteed Effective Control Strategies , 1991, ML.

[14]  Gerald DeJong,et al.  Utility Generalization and Composability Problems in Explanation-Based Learning. , 1991 .

[15]  Paul E. Utgoff,et al.  Two Kinds of Training Information For Evaluation Function Learning , 1991, AAAI.

[16]  Gerald DeJong,et al.  A Framework of Simplifications in Learning to Plan , 1992 .

[17]  Tom M. Mitchell,et al.  Learning by experimentation: acquiring and refining problem-solving heuristics , 1993 .

[18]  Dale Schuurmans,et al.  Probabilistic , 2019, 99 Variations on a Proof.