Research map / Reinforcement learning / Visual and representation RL
General Policies, Representations, and Planning Width
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 |
|---|---|---|---|
| Add the rule {¬H} → {H, p?, t?} (ablation) | Delivery sketches · Delivery-1 (QD1) | sketch width: 2 -> 1 | Helped |
| Add the rule {¬H} → {H, p?, t?} (ablation) | Delivery sketches · Delivery (QD) | sketch width | No clear effect |
| Add the rule {n > 0} → {n↓, H?, p?, t?} (ablation) | Delivery sketches · Delivery (QD) | sketch width: unb -> 2 | Helped |
| Combine the rules in σ2 and σ4 (ablation) | Delivery sketches · Delivery (QD) | sketch width: 2 -> 1 | Helped |
| Add the rule {¬H, p > 0} → {p↓, t?} (ablation) | Delivery sketches · Delivery-1 (QD1) | sketch width: 2 | No clear effect |
| Add the rule {¬H, p > 0} → {p↓, t?} (ablation) | Delivery sketches · Delivery (QD) | sketch width | No clear effect |
| Add the rule {H, t > 0} → {t↓, p?} (ablation) | Delivery sketches · Delivery-1 (QD1) | sketch width: 2 | No clear effect |
| Add the rule {H, t > 0} → {t↓, p?} (ablation) | Delivery sketches · Delivery (QD) | sketch width | No clear effect |
| Combine the rules in σ2, σ4, σ6, and σ7 (ablation) | Delivery sketches · Delivery-1 (QD1) | sketch width: 1 -> 0 | Helped |
| Combine the rules in σ2, σ4, σ6, and σ7 (ablation) | Delivery sketches · Delivery (QD) | sketch width: 1 -> 0 | Helped |
Closest papers by meaning
- Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning (NeurIPS 2026 · similarity 0.91)
- Learning Planning Domains from Non-redundant Fully-Observed Traces: Theoretical Foundations and Complexity Analysis (AAAI 2024 · similarity 0.89)
- Towards Practical Classical Planning Compilations of Numeric Planning (AAAI 2025 · similarity 0.88)
- Symbolic Numeric Planning with Patterns (AAAI 2024 · similarity 0.88)
- An Automatic Sound and Complete Abstraction Method for Generalized Planning with Baggable Types (AAAI 2025 · similarity 0.86)
- On the Computational Complexity of Plan Verification, (Bounded) Plan-Optimality Verification, and Bounded Plan Existence (AAAI 2024 · similarity 0.86)
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.