Hybrid learning of search control for partial-order planning

This paper presents results on applying a version of the Dolphin search-control learning system to speed up a partial-order planner. Dolphin integrates explanation-based and inductive learning techniques to acquire e ective clause-selection rules for Prolog programs. A version of the UCPOP partial-order planning algorithm has been implemented as a Prolog program and Dolphin used to automatically learn domain-speci c search control rules that help eliminate backtracking. The resulting system is shown to produce signi cant speedup in several planning domains.

[1]  Gerald DeJong,et al.  COMPOSER: A Probabilistic Solution to the Utility Problem in Speed-Up Learning , 1992, AAAI.

[2]  Steven Minton,et al.  Small is Beautiful: A Brute-Force Approach to Learning First-Order Formulas , 1994, AAAI.

[3]  Saso Dzeroski,et al.  Inductive Logic Programming: Techniques and Applications , 1993 .

[4]  Oren Etzioni,et al.  PRODIGY4.0: The Manual and Tutorial , 1992 .

[5]  David Croft.  Choices made by a planner : identifying them, and improving the way in which they are made , 1985 .

[6]  Steven Minton,et al.  Total Order vs. Partial Order Planning: Factors Influencing Performance , 1992, KR.

[7]  Manuela M. Veloso,et al.  Incremental Learning of Control Knowledge for Nonlinear Problem Solving , 1994, ECML.

[8]  Tom Michael Mitchell,et al.  Explanation-based generalization: A unifying view , 1986 .

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

[10]  Oren Etzioni,et al.  Explanation-Based Learning: A Problem Solving Perspective , 1989, Artif. Intell..

[11]  Roberto Desimone,et al.  Learning Control Knowledge Within an Explanation-Based Learning Framework , 1987, EWSL.

[12]  Anthony Barrett,et al.  Partial-Order Planning: Evaluating Possible Efficiency Gains , 1994, Artificial Intelligence.

[13]  Daniel S. Weld,et al.  UCPOP: A Sound, Complete, Partial Order Planner for ADL , 1992, KR.

[14]  Raymond J. Mooney,et al.  Combining FOIL and EBG to Speed-up Logic Programs , 1993, IJCAI.

[15]  Manuela Veloso,et al.  Incremental Learning of Control Knowledge for Improvement of Planning Efficiency and Plan Quality , 1994 .

[16]  Ingrid Zukerman,et al.  An Inductive Approach to Learning Search Control Rules for Planning , 1993, IJCAI.

[17]  John M. Zelle,et al.  Learning Search-Control Heuristics For Logic Programs: Applications ToSpeed-up Learning and LanguageAcquisitions , 1993 .

[18]  Subbarao Kambhampati,et al.  Learning Expla sed Search Control Rules For Partial Order Planning , 1994 .

[19]  Manuela Veloso.  Learning by analogical reasoning in general problem-solving , 1992 .

[20]  Jaime G. Carbonell,et al.  Control Knowledge to Improve Plan Quality , 1994, AIPS.

[21]  Subbarao Kambhampati,et al.  Relative Utility of EBG based Plan Reuse in Partial Ordering vs. Total Ordering Planning , 1993, AAAI.

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