Research map / Probabilistic and scientific modeling / Molecules and proteins
Latent Planning via Expansive Tree Search
Robert Gieselmann, Florian T. Pokorny
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 |
|---|---|---|---|
| add NCE transition-density rejection during planning (ablation) | ELAST · BlockS hard | success rate (%): 51 ± 4 -> 96 ± 3 | Improved |
| add NCE transition-density rejection during planning (ablation) | ELAST · Cable | success rate (%): 25 ± 5 -> 95 ± 2 | Improved |
| add NCE transition-density rejection during planning (ablation) | ELAST · BlockAsym | success rate (%): 73 ± 5 -> 100 ± 0 | Improved |
| add tree rewiring (tree optimization) (ablation) | ELAST · BlockS hard | success rate (%): 40 ± 4 -> 96 ± 3 | Improved |
| add tree rewiring (tree optimization) (ablation) | ELAST · Button | success rate (%): 50 ± 2 -> 88 ± 5 | Improved |
| add tree rewiring (tree optimization) (ablation) | ELAST · BlockS hard | average trajectory length (steps): 93 ± 2 -> 36 ± 1 | Improved |
| add tree rewiring (tree optimization) (ablation) | ELAST · Button | average trajectory length (steps): 72 ± 5 -> 38 ± 6 | Improved |
| set sparse node sampling bias p_sparse from 0.0 to 0.78 (ablation) | ELAST · BlockAsym | success rate (%): 0% -> 100 ± 0 | Improved |
| use ELAST tree-search planning instead of CEM on the same CPC embedding (ablation) | CPC embedding · BlockS hard | success rate (%): 9 ± 4 -> 96 ± 3 | Improved |
| use ELAST tree-search planning instead of CEM on the same CPC embedding (ablation) | CPC embedding · Hammer | success rate (%): 0 ± 0 -> 22 ± 2 | Improved |
| use ELAST tree-search planning instead of collocation on the same CPC embedding (ablation) | CPC embedding · BlockAsym | success rate (%): 0 ± 0 -> 96 ± 3 | Improved |
| plan in latent space instead of image-space HTM graph | ELAST · Button | success rate (%): 45 ± 4 -> 88 ± 5 | Improved |
Closest papers by meaning
- Latent Plan Transformer for Trajectory Abstraction: Planning as Latent Space Inference (NeurIPS 2024 · similarity 0.88)
- Efficient Planning with Latent Diffusion (ICLR 2024 · similarity 0.88)
- Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning (NeurIPS 2026 · similarity 0.87)
- PcLast: Discovering Plannable Continuous Latent States (ICML 2024 · similarity 0.87)
- Scalable Decision-Making in Stochastic Environments through Learned Temporal Abstraction (ICLR 2025 · similarity 0.87)
- Tree-Guided Diffusion Planner (NeurIPS 2025 · similarity 0.87)
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.
