Research map / Probabilistic and scientific modeling / Molecules and proteins
Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary
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 14-step rather than 7-step random-walk instances | LatPlan + AMA2 · MNIST 8-puzzle, std | solved instances out of 100: 72 -> 6 | Hurt |
| Use 14-step rather than 7-step random-walk instances | LatPlan + AMA2 · Mandrill 8-puzzle, std | solved instances out of 100: 100 -> 9 | Hurt |
| Use 14-step rather than 7-step random-walk instances | LatPlan + AMA2 · Spider 8-puzzle, std | solved instances out of 100: 94 -> 29 | Hurt |
| Use 14-step rather than 7-step random-walk instances | LatPlan + AMA2 · LightsOut, std | solved instances out of 100: 100 -> 59 | Hurt |
| Use 14-step rather than 7-step random-walk instances | LatPlan + AMA2 · Twisted LightsOut, std | solved instances out of 100: 96 -> 75 | Hurt |
| Add Gaussian input noise | LatPlan + AMA2 · MNIST 8-puzzle, benchmark A | solved instances out of 100: 72 -> 64 | Hurt |
| Add Gaussian input noise | LatPlan + AMA2 · Mandrill 8-puzzle, benchmark A | solved instances out of 100: 100 -> 100 | No clear effect |
| Add Gaussian input noise | LatPlan + AMA2 · Spider 8-puzzle, benchmark A | solved instances out of 100: 94 -> 99 | Helped |
| Add Gaussian input noise | LatPlan + AMA2 · LightsOut, benchmark A | solved instances out of 100: 100 -> 99 | Hurt |
| Add Gaussian input noise | LatPlan + AMA2 · Twisted LightsOut, benchmark A | solved instances out of 100: 96 -> 65 | Hurt |
Closest papers by meaning
- PcLast: Discovering Plannable Continuous Latent States (ICML 2024 · similarity 0.87)
- Differentiable Learning of Lifted Action Schemas for Classical Planning (NeurIPS 2026 · similarity 0.87)
- State Encodings for GNN-Based Lifted Planners (AAAI 2025 · similarity 0.87)
- System 1.x: Learning to Balance Fast and Slow Planning with Language Models (ICLR 2025 · similarity 0.86)
- Embodied Task Planning via Graph-Informed Action Generation with Large Language Models (ICML 2026 · similarity 0.86)
- Graph Neural Network Based Action Ranking for Planning (NeurIPS 2025 · 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.