What type of study is this?

This is a Experimental Study study.

September 17, 2025Proceedings of the International Conference on Automated Planning and Scheduling0 citationsOpen Access

Enhanced Classical Planning Through Action Relational Structures and Learning Algorithms

Leveraging Action Relational Structures for Integrated Learning and Planning

View Full Paper

Authors

RWRuiqi Wang FTFelipe Trevizan

Discussion

Member takes

Overview

This approach introduces partial-space search for classical planning, suggesting improvements through action set heuristics and efficient learning integration.

Key Points

LazyLifted outperforms state-of-the-art ML-based heuristics on IPC 2023 learning benchmarks while utilizing partial-space search.
By leveraging PDDL action schemas, action set heuristics provide a granular view that enhances search efficiencies in classical planning.
This research automates the conversion of existing heuristics into optimized action set heuristics for improved planning accuracy.
Efficient performance is demonstrated in high branching factor tasks, showcasing the advantages of integrating search algorithms with learning methods.

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/68d4566c31b076d99fa5bb60 https://doi.org/10.1609/icaps.v35i1.36128

Ask AI

Helpful

Bookmark

View Full Paper

September 17, 2025Proceedings of the International Conference on Automated Planning and Scheduling0 citationsOpen Access

Enhanced Classical Planning Through Action Relational Structures and Learning Algorithms

Leveraging Action Relational Structures for Integrated Learning and Planning

View Full Paper

Authors

RWRuiqi Wang FTFelipe Trevizan

Discussion

Member takes

Overview

This approach introduces partial-space search for classical planning, suggesting improvements through action set heuristics and efficient learning integration.

Key Points

LazyLifted outperforms state-of-the-art ML-based heuristics on IPC 2023 learning benchmarks while utilizing partial-space search.
By leveraging PDDL action schemas, action set heuristics provide a granular view that enhances search efficiencies in classical planning.
This research automates the conversion of existing heuristics into optimized action set heuristics for improved planning accuracy.
Efficient performance is demonstrated in high branching factor tasks, showcasing the advantages of integrating search algorithms with learning methods.

Ask AI

Helpful

Bookmark

View Full Paper

Cite This Study

Wang et al. (2025) studied this question.

synapsesocial.com/papers/68d4566c31b076d99fa5bb60 https://doi.org/10.1609/icaps.v35i1.36128

Ask AI

Helpful

Bookmark

View Full Paper