What Matters in Hierarchical Search for Combinatorial Reasoning Problems?
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909488247734272 |
|---|---|
| author | Zawalski, Michał Góral, Gracjan Tyrolski, Michał Wiśnios, Emilia Budrowski, Franciszek Cygan, Marek Kuciński, Łukasz Miłoś, Piotr |
| author_facet | Zawalski, Michał Góral, Gracjan Tyrolski, Michał Wiśnios, Emilia Budrowski, Franciszek Cygan, Marek Kuciński, Łukasz Miłoś, Piotr |
| contents | Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enhance planning by incorporating hierarchical high-level search strategies, known as subgoal methods. While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts. In this study, we conduct an in-depth exploration of subgoal-planning methods for combinatorial reasoning. We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts. We propose a consistent evaluation methodology to achieve meaningful comparisons between methods and reevaluate the state-of-the-art algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03361 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | What Matters in Hierarchical Search for Combinatorial Reasoning Problems? Zawalski, Michał Góral, Gracjan Tyrolski, Michał Wiśnios, Emilia Budrowski, Franciszek Cygan, Marek Kuciński, Łukasz Miłoś, Piotr Machine Learning Efficiently tackling combinatorial reasoning problems, particularly the notorious NP-hard tasks, remains a significant challenge for AI research. Recent efforts have sought to enhance planning by incorporating hierarchical high-level search strategies, known as subgoal methods. While promising, their performance against traditional low-level planners is inconsistent, raising questions about their application contexts. In this study, we conduct an in-depth exploration of subgoal-planning methods for combinatorial reasoning. We identify the attributes pivotal for leveraging the advantages of high-level search: hard-to-learn value functions, complex action spaces, presence of dead ends in the environment, or using data collected from diverse experts. We propose a consistent evaluation methodology to achieve meaningful comparisons between methods and reevaluate the state-of-the-art algorithms. |
| title | What Matters in Hierarchical Search for Combinatorial Reasoning Problems? |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.03361 |