A Framework of Simplifications in Learning to Plan

Learning shows great promise to extend the generality and effectiveness of planning techniques. Research in this area has generated an impressive battery of techniques and a growing body of empirical successes. Unfortunately the formal properties of these systems are not well understood. This is highlighted by a growing corpus of demonstrations where learning actually degrades planning performance. In this paper we view learning to plan as a search problem. We argue that the complexity of this search precludes a general solution and can only be approached by making simplifying assumptions. We discuss the frequently unarticulated commitments which underly current learning approaches. From these we assemble a framework of simplifications which a learning planner can draw upon. These simplifications improve learning efficiency but not without tradeoffs.

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

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

[3]  Craig A. Knoblock.  Learning Abstraction Hierarchies for Problem Solving , 1990, AAAI.

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

[5]  Shavlik.  Generalizing the structure of explanations in explanation-based learning. Doctoral thesis , 1987 .

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

[7]  David E. Smith,et al.  Ordering Conjunctive Queries , 1985, Artif. Intell..

[8]  Marcel Schoppers,et al.  Universal Plans for Reactive Robots in Unpredictable Environments , 1987, IJCAI.

[9]  Raymond J. Mooney,et al.  First-Order Theory Revision , 1991, ML.

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

[11]  Michael P. Wellman.  Formulation of tradeoffs in planning under uncertainty , 1988 .

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

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

[14]  Jude Shavlik,et al.  Refinement ofApproximate Domain Theories by Knowledge-Based Neural Networks , 1990, AAAI.

[15]  Ingrid Zukerman,et al.  Learning Search Control Rules for Planning: An Inductive Approach , 1991, ML.

[16]  Balas K. Natarajan,et al.  On learning from exercises , 1989, COLT '89.

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

[18]  Robert V. Hogg,et al.  Introduction to Mathematical Statistics. , 1966 .

[19]  John L. Bresina,et al.  Anytime Synthetic Projection: Maximizing the Probability of Goal Satisfaction , 1990, AAAI.

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

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

[22]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

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

[24]  Pekka Orponen,et al.  Probably Approximately Optimal Derivation Strategies , 1991, KR.

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

[26]  Yong Ma,et al.  Sociopathic Knowledge Bases: Correct Knowledge Can Be Harmful Even Given Unlimited Computation , 1989 .

[27]  David Ruby,et al.  SteppingStone: An Empirical and Analytical Evaluation , 1991, AAAI.

[28]  Richard E. Korf,et al.  Macro-Operators: A Weak Method for Learning , 1985, Artif. Intell..

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

[30]  David Chapman,et al.  Planning for Conjunctive Goals , 1987, Artif. Intell..

[31]  Monte Zweben,et al.  Learning Search Control for Constraint-Based Scheduling , 1990, AAAI.

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

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

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

[35]  Prasad Tadepalli.  Learning with Incrutable Theories , 1991, ML.