Research map / Label-efficient and robust learning / Domain adaptation and generalization
Refining HTN Methods via Task Insertion with Preferences
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use less complete input methods (MR-M or MR-L instead of MR-H) (ablation) | MethodRefine · Logistics, Satellite, and Blocks-world testing instances | solving rate | Hurt |
| Increase the number of training instances | MethodRefine · Logistics, Satellite, and Blocks-world testing instances | solving rate | Helped |
| Use stratum-based prioritization rather than abstract-task-first prioritization (ablation) | MethodRefine · Logistics, Satellite, and Blocks-world testing instances (MR-M) | solving rate | Helped |
| Use no preference rather than stratum-based prioritization (ablation) | MethodRefine · Logistics, Satellite, and Blocks-world testing instances (MR-M) | solving rate | Hurt |
| Prioritize inserting tasks into abstract compound tasks (MR-M-Abs) (ablation) | MethodRefine · Logistics, Satellite, and Blocks-world testing instances (MR-M) | solving rate | Hurt |
| Replace MethodRefine with HTN-MAKER | MethodRefine · Logistics, Satellite, and Blocks-world testing instances | solving rate | Mixed |
| Learn methods from acyclic decomposition trees rather than allowing recursive learned methods | MethodRefine · Satellite testing instances | solving rate | Helped |
Closest papers by meaning
- Learning Hierarchical Task Knowledge for Planning (AAAI 2025 · similarity 0.89)
- Learning Domain-Independent Heuristics for Grounded and Lifted Planning (AAAI 2024 · similarity 0.84)
- Quantifying Task Priority for Multi-Task Optimization (CVPR 2024 · similarity 0.83)
- On the Computational Complexity of Plan Verification, (Bounded) Plan-Optimality Verification, and Bounded Plan Existence (AAAI 2024 · similarity 0.83)
- HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming (ICML 2024 · similarity 0.83)
- PlanDQ: Hierarchical Plan Orchestration via D-Conductor and Q-Performer (ICML 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.