Pattern Selection for Optimal Classical Planning with Saturated Cost Partitioning

Seipp, Jendrik

doi:10.24963/ijcai.2019/780

Cited by 5 publications

(5 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Trading off time for improved heuristic quality should hence improve performance. Several enhancements that could be used here have been proposed for saturated cost partitioning, e.g., using multiple cost partitions (Seipp, Keller, and Helmert 2020), or using abstractions from a larger set as long as resources permit (Seipp 2019).…”

Section: Future Workmentioning

confidence: 99%

Dantzig-Wolfe Decomposition for Cost Partitioning

Pommerening

Keller

Halasi³

et al. 2021

ICAPS

Self Cite

View full text Add to dashboard Cite

Optimal cost partitioning can produce high quality heuristic estimates even from small abstractions. It can be computed with a linear program (LP) but the size of this LP often makes this impractical. Recent work used Lagrangian decomposition to speed up the computation. Here we use a different decomposition technique called Dantzig-Wolfe decomposition to tackle the problem. This gives new insights into optimal cost partitioning and has several advantages over Lagrangian decomposition: our method detects when a cost partition is optimal; it can deal with general cost functions; and it does not consider abstractions in the linear program that do not contribute to the heuristic value. We also show the advantage of the method empirically and investigate several improvements that are useful for all cost partitioning methods.

show abstract

Section: Future Workmentioning

confidence: 99%

Dantzig-Wolfe Decomposition for Cost Partitioning

Pommerening

Keller

Halasi³

et al. 2021

ICAPS

Self Cite

View full text Add to dashboard Cite

show abstract

“…A common approach to solving classical planning tasks optimally is A * search (Hart, Nilsson, and Raphael 1968) with an admissible heuristic (e.g., Helmert and Domshlak 2009;Karpas and Domshlak 2009;Katz and Domshlak 2010;Pommerening et al 2015;Sievers and Helmert 2021). Heuristics based on abstractions of the planning task have been particularly successful (e.g., Franco et al 2017;Seipp 2019;Drexler, Seipp, and Speck 2021;Kreft et al 2023).…”

Section: Introductionmentioning

confidence: 99%

“…Since domain abstractions and especially PDBs do not allow for fine-grained refinement, it is infeasible to solve nontrivial tasks while refining these types of abstractions. Therefore, existing approaches for these abstraction types mainly create collections of abstractions focusing on different aspects of the task (e.g., Haslum et al 2007;Pommerening, Röger, and Helmert 2013;Franco et al 2017;Seipp 2019).…”

Section: Introductionmentioning

confidence: 99%

Efficiently Computing Transitions in Cartesian Abstractions

Seipp

2024

ICAPS

View full text Add to dashboard Cite

Counterexample-guided Cartesian abstraction refinement yields strong heuristics for optimal classical planning. The approach iteratively finds a new abstract solution, checks where it fails for the original task and refines the abstraction to avoid the same failure in subsequent iterations. The main bottleneck of this refinement loop is the memory needed for storing all abstract transitions. To address this issue, we introduce an algorithm that efficiently computes abstract transitions on demand. This drastically reduces the memory consumption and allows us to solve tasks during the refinement loop and during the search that were previously out of reach.

show abstract

“…Heuristic search has been extremely successful in AI planning (e. g. [2,12,10,22,25]). But this research has almost exclusively been based on grounded (propositional) task representations, in contrast to the lifted PDDL input models, that employ variables ranging over a finite universe of objects.…”

Section: Introductionmentioning

confidence: 99%

A Landmark-Cut Heuristic for Lifted Optimal Planning

Wichlacz,

Höller,

Fišer

et al. 2023

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

Lifted planning – finding plans directly on the PDDL input model – has attracted renewed attention during the last years. This avoids the process of grounding, which can become computationally prohibitive very easily. However, the main focus of recent research in this area has been on satisficing, i.e., (potentially) suboptimal planning. We present a novel heuristic for optimal lifted planning. Our basic idea is inspired by the LM-cut heuristic, which has been very successful in grounded optimal planning. Like LM-cut, we generate cut-based landmarks via back-chaining from the goal, generating cuts of partially grounded actions. However, exactly mimicking the ground formulation is not feasible, this includes computing the hmax heuristic several times for one computation of the LM-cut heuristic (which is already NP-hard to compute). We show that our heuristic is admissible and evaluate it in a cost optimal setting.

show abstract

Pattern Selection for Optimal Classical Planning with Saturated Cost Partitioning

Cited by 5 publications

References 24 publications

Dantzig-Wolfe Decomposition for Cost Partitioning

Dantzig-Wolfe Decomposition for Cost Partitioning

Efficiently Computing Transitions in Cartesian Abstractions

A Landmark-Cut Heuristic for Lifted Optimal Planning

Contact Info

Product

Resources

About