Research map / Reinforcement learning / Visual and representation RL
Action Schema Networks: Generalised Policies With Deep Learning
Sam Toyer, Felipe Trevizan, Sylvie Thiébaux, Lexing Xie
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 |
|---|---|---|---|
| Use LM-cut landmark features as network inputs (ablation) | ASNet · Probabilistic Blocks World, extended tests with 10–35 blocks | coverage | Improved |
| Use LM-cut landmark features as network inputs (ablation) | ASNet · CosaNostra Pizza test set | coverage | Improved |
| Omit LM-cut input features (ablation) | ASNet (h-add) · Triangle Tire World, sizes 15 and 20 | solution time: 2.4x; 4.3x | Improved |
| Train with potentially suboptimal h-add teacher policies instead of optimal policies (ablation) | ASNet · Probabilistic Blocks World | ability to converge within the training time limit | Improved |
| Increase network depth to provide enough layers to see the hazard (ablation) | ASNet · Monster, path length 5 | coverage: 14/30 -> 30/30 | Improved |
| Increase network depth to provide enough layers to see the hazard (ablation) | ASNet · Monster, path length 4 | coverage: 14/30 -> 30/30 | Improved |
| Omit LM-cut input features (ablation) | ASNet (h-add) · Probabilistic Blocks World, problems up to 20 blocks | solution cost: 65.93 ± 2.39 vs 70.33 ± 2.51; 69.53 ± 2.81 vs 77.30 ± 2.60 | Mixed |
Closest papers by meaning
- Differentiable Learning of Lifted Action Schemas for Classical Planning (NeurIPS 2026 · similarity 0.88)
- Graph Neural Network Based Action Ranking for Planning (NeurIPS 2025 · similarity 0.88)
- Learning More Expressive General Policies for Classical Planning Domains (AAAI 2025 · similarity 0.86)
- System 1.x: Learning to Balance Fast and Slow Planning with Language Models (ICLR 2025 · similarity 0.85)
- PcLast: Discovering Plannable Continuous Latent States (ICML 2024 · similarity 0.85)
- Efficient Lookahead Encoding and Abstracted Width for Learning General Policies in Classical Planning (NeurIPS 2026 · 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.
