Research map / Learning theory and algorithms / Combinatorial and search optimization
Interpretable and Personalized Apprenticeship Scheduling: Learning Interpretable Scheduling Policies from Heterogeneous User Demonstrations
Rohan Paleja, Andrew Silva, Letian Chen, Matthew Gombolay
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| discretize PNT into interpretable form | PNT · Synthetic scheduling | accuracy: 96.13 -> 99.66 | Improved |
| discretize PNT into interpretable form | PNT · Synthetic low-dim | accuracy: 97.30 -> 96.13 | Hurt |
| discretize PNT into interpretable form | PNT · Taxi domain | accuracy: 88.22 -> 77.73 | Hurt |
| PNT-learned embeddings appended to states for DT (ablation) | Decision tree · Taxi domain | accuracy: 74.90 -> 87.85 | Improved |
| DT with embeddings omega instead of vanilla DT (ablation) | Decision tree · Synthetic scheduling | accuracy: 32.4 -> 32.85 | No clear effect |
| DT with embeddings omega instead of vanilla DT (ablation) | Decision tree · Synthetic low-dim | accuracy: 55.76 -> 53.66 | No clear effect |
| personalized embedding PNT versus best baseline DDT | PNT · Synthetic scheduling | accuracy: 52.35 -> 96.13 | Improved |
| PNT versus InfoGAIL | PNT · Synthetic scheduling | accuracy: 25.72 -> 96.13 | Improved |
| pretrain PNT then DAgger instead of random init DAgger | PNT · Synthetic scheduling | successful schedule completion: +28.57% | Improved |
| pretrain PNT then DAgger instead of random init DAgger | PNT · Synthetic scheduling | tasks completed before failure: +12.5% | Improved |
| tree-based PNT versus neural network | Counterfactual PNT · User study (20 participants) | simulation correctness | Improved |
| tree-based PNT versus neural network | Counterfactual PNT · User study (20 participants) | time to compute output | Improved |
Closest papers by meaning
- OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation (NeurIPS 2025 · similarity 0.86)
- SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution (CVPR 2024 · similarity 0.84)
- Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning (AAAI 2024 · similarity 0.83)
- From Instance Training to Instruction Learning: Task Adapters Generation from Instructions (NeurIPS 2024 · similarity 0.82)
- PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization (ICLR 2024 · similarity 0.82)
- DynaSchedBench: Calibrated Dynamic Scheduling Benchmarks and Observability Paradox in LLM-based Scheduling Agents (ICML 2026 · similarity 0.82)
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.
