Portfolio-based planning: State of the art, common practice and open challenges

In recent years the field of automated planning has significantly advanced and several powerful domain-independent planners have been developed. However, none of these systems clearly outperforms all the others in every known benchmark domain. This observation motivated the idea of configuring and exploiting a portfolio of planners to perform better than any individual planner: some recent planning systems based on this idea achieved significantly good results in experimental analysis and International Planning Competitions. Such results let us suppose that future challenges of the Automated Planning community will converge on designing different approaches for combining existing planning algorithms. This paper reviews existing techniques and provides an exhaustive guide to portfolio-based planning. In addition, the paper outlines open issues of existing approaches and highlights possible future evolution of these techniques.

[1]  W. Sharpe.  Portfolio Theory and Capital Markets , 1970 .

[2]  Bart Selman,et al.  Algorithm portfolios , 2001, Artif. Intell..

[3]  Scott Sanner,et al.  A Survey of the Seventh International Planning Competition , 2012, AI Mag..

[4]  E. Dahlman,et al.  A Critical Assessment of Benchmark Comparison in Planning , 2002, J. Artif. Intell. Res..

[5]  Y. Censor.  Pareto optimality in multiobjective problems , 1977 .

[6]  Joao Marques-Silva,et al.  A MAX-SAT Algorithm Portfolio , 2008, ECAI.

[7]  Jörg Hoffmann,et al.  Optimizing Planning Domains by Automatic Action Schema Splitting , 2014, ICAPS.

[8]  Yixin Chen,et al.  Temporal Planning using Subgoal Partitioning and Resolution in SGPlan , 2006, J. Artif. Intell. Res..

[9]  Kevin Leyton-Brown,et al.  Improved Features for Runtime Prediction of Domain-Independent Planners , 2014, ICAPS.

[10]  Kevin Leyton-Brown,et al.  Evaluating Component Solver Contributions to Portfolio-Based Algorithm Selectors , 2012, SAT.

[11]  Kevin Leyton-Brown,et al.  Sequential Model-Based Optimization for General Algorithm Configuration , 2011, LION.

[12]  Malik Ghallab,et al.  Chapter 14 – Temporal Planning , 2004 .

[13]  Nathan R. Sturtevant,et al.  ArvandHerd 2014 , 2014 .

[14]  Martin Müller,et al.  Monte-Carlo Exploration for Deterministic Planning , 2009, IJCAI.

[15]  Marius Thomas Lindauer,et al.  A Portfolio Solver for Answer Set Programming: Preliminary Report , 2011, LPNMR.

[16]  A. Howe,et al.  Learned Models of Performance for Many Planners , 2007 .

[17]  Nathan R. Sturtevant,et al.  ArvandHerd: Parallel Planning with a Portfolio , 2012, ECAI.

[18]  Alfonso Gerevini,et al.  Automatic Generation of Efficient Domain-Optimized Planners from Generic Parametrized Planners , 2013, SOCS.

[19]  Kevin Leyton-Brown,et al.  HAL: A Framework for the Automated Analysis and Design of High-Performance Algorithms , 2011, LION.

[20]  Sergio Jiménez Celorrio,et al.  The deterministic part of the seventh International Planning Competition , 2015, Artif. Intell..

[21]  Tad Hogg,et al.  An Economics Approach to Hard Computational Problems , 1997, Science.

[22]  M. Helmert,et al.  Fast Downward Stone Soup : A Baseline for Building Planner Portfolios , 2011 .

[23]  Adele E. Howe,et al.  Exploiting Competitive Planner Performance , 1999, ECP.

[24]  Blai Bonet,et al.  A Concise Introduction to Models and Methods for Automated Planning , 2013, A Concise Introduction to Models and Methods for Automated Planning.

[25]  Jendrik Seipp,et al.  Automatic Configuration of Sequential Planning Portfolios , 2015, AAAI.

[26]  A. Howe,et al.  Directing a Portfolio with Learning , 2006 .

[27]  John Levine,et al.  Learning Macro-Actions for Arbitrary Planners and Domains , 2007, ICAPS.

[28]  Barry O'Sullivan,et al.  Evolving Instance Specific Algorithm Configuration , 2021, SOCS.

[29]  Luca Pulina,et al.  A Multi-engine Solver for Quantified Boolean Formulas , 2007, CP.

[30]  Peter Auer,et al.  Finite-time Analysis of the Multiarmed Bandit Problem , 2002, Machine Learning.

[31]  Adele E. Howe,et al.  Learning from planner performance , 2009, Artif. Intell..

[32]  J. Ho,et al.  The Metric FF Planning System Translating Ignoring Delete Lists to Numeric State Variables , 2003 .

[33]  Thomas Leo McCluskey,et al.  On Exploiting Structures of Classical Planning Problems: Generalizing Entanglements , 2012, ECAI.

[34]  W. Marsden.  I and J , 2012 .

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

[36]  Silvan Sievers.  Fast Downward Cedalion , 2014 .

[37]  Fernando Fernández,et al.  Learning Predictive Models to Configure Planning Portfolios , 2013 .

[38]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[39]  Alfonso Gerevini,et al.  PbP2: Automatic Configuration of a Portfolio-based Multi-Planner , 2011, ICAPS 2011.

[40]  Bart Selman,et al.  Unifying SAT-based and Graph-based Planning , 1999, IJCAI.

[41]  Raquel Fuentetaja,et al.  Improving Control-Knowledge Acquisition for Planning by Active Learning , 2006, ECML.

[42]  Marc Schoenauer,et al.  Multi-objective AI Planning: Evaluating DaE YAHSP on a Tunable Benchmark , 2013, EMO.

[43]  Jussi Rintanen.  Engineering Efficient Planners with SAT , 2012, ECAI.

[44]  J. Christopher Beck,et al.  itSIMPLE4.0: Enhancing the Modeling Experience of Planning Problems , 2012 .

[45]  Alan Fern,et al.  The first learning track of the international planning competition , 2011, Machine Learning.

[46]  Alfonso Gerevini,et al.  An Automatically Configurable Portfolio-based Planner with Macro-actions: PbP , 2009, ICAPS.

[47]  Silvia Richter,et al.  The LAMA Planner: Guiding Cost-Based Anytime Planning with Landmarks , 2010, J. Artif. Intell. Res..

[48]  Malte Helmert,et al.  The Fast Downward Planning System , 2006, J. Artif. Intell. Res..

[49]  Kevin Leyton-Brown,et al.  Algorithm runtime prediction: Methods & evaluation , 2012, Artif. Intell..

[50]  Ronen I. Brafman,et al.  Distributed Heuristic Forward Search for Multi-agent Planning , 2014, J. Artif. Intell. Res..

[51]  Bernhard Nebel,et al.  COMPLEXITY RESULTS FOR SAS+ PLANNING , 1995, Comput. Intell..

[52]  John R. Rice,et al.  The Algorithm Selection Problem , 1976, Adv. Comput..

[53]  Kevin Leyton-Brown,et al.  SATzilla: Portfolio-based Algorithm Selection for SAT , 2008, J. Artif. Intell. Res..

[54]  Lukás Chrpa,et al.  An Automatic Algorithm Selection Approach for Planning , 2013, 2013 IEEE 25th International Conference on Tools with Artificial Intelligence.

[55]  Fernando Fernández,et al.  IBACOP and IBACOP2 Planner , 2014 .

[56]  Paolo Traverso,et al.  Automated Planning: Theory & Practice , 2004 .

[57]  Jendrik Seipp,et al.  Learning Portfolios of Automatically Tuned Planners , 2012, ICAPS.

[58]  Ian Horrocks,et al.  Combinations of Modal Logics , 2002, Artificial Intelligence Review.

[59]  Silvia Richter,et al.  Landmark-Based Heuristics and Search Control for Automated Planning (Extended Abstract) , 2013, IJCAI.

[60]  Robert Givan,et al.  Learning Domain-Specific Control Knowledge from Random Walks , 2004, ICAPS.

[61]  Ivan Serina,et al.  Planning Through Stochastic Local Search and Temporal Action Graphs in LPG , 2003, J. Artif. Intell. Res..

[62]  Alfonso Gerevini,et al.  Planning through Automatic Portfolio Configuration: The PbP Approach , 2014, J. Artif. Intell. Res..

[63]  Daniel Borrajo,et al.  Performance Analysis of Planning Portfolios , 2012, SOCS.