Research map / Reinforcement learning / Visual and representation RL
What Planning Problems Can A Relational Neural Network Solve?
Jiayuan Mao, Tomás Lozano-Pérez, Joshua B. Tenenbaum, Leslie Pack Kaelbling
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 |
|---|---|---|---|
| increase RelNN depth from 1 to 2 layers (ablation) | RelNN[D,2] · Assembly3 n=30 | success rate: 0.02 -> 1.0 | Improved |
| increase RelNN depth from 1 to 2 layers (ablation) | RelNN[D,2] · Assembly3 n=10 | success rate: 0.2 -> 1.0 | Improved |
| use depth f(n)=n/5+1 instead of constant depth 3 (ablation) | RelNN[D,2] · Logistics n=30 | success rate: 0.30 -> 1.0 | Improved |
| use depth f(n)=n/5+1 instead of constant depth 3 (ablation) | RelNN[D,2] · Logistics n=50 | success rate: 0.23 -> 1.0 | Improved |
| use depth f(n)=n/5+1 instead of constant depth 3 (ablation) | RelNN[D,2] · Logistics n=10 | success rate: 1.0 -> 1.0 | No clear effect |
| use depth f(n)=n/10+3 instead of constant depth 3 (ablation) | RelNN[D,2] · BlocksWorld-Clear n=50 | average solution length: 15.7 -> 3.5 | Improved |
| use depth f(n)=n/10+3 instead of constant depth 3 (ablation) | RelNN[D,2] · BlocksWorld-Clear n=10 | average solution length: 2.9 -> 2.5 | Improved |
| use depth f(n)=n/10+3 instead of constant depth 3 (ablation) | RelNN[D,2] · BlocksWorld-Clear | success rate: 1.0 -> 1.0 | No clear effect |
Closest papers by meaning
- Graph Neural Network Based Action Ranking for Planning (NeurIPS 2025 · similarity 0.86)
- Graph Learning for Numeric Planning (NeurIPS 2024 · similarity 0.86)
- Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning (NeurIPS 2026 · similarity 0.86)
- Learning More Expressive General Policies for Classical Planning Domains (AAAI 2025 · similarity 0.86)
- Learning Domain-Independent Heuristics for Grounded and Lifted Planning (AAAI 2024 · similarity 0.85)
- Symbolic Numeric Planning with Patterns (AAAI 2024 · similarity 0.85)
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.
