Research map / Reinforcement learning / Visual and representation RL
Learning to Plan in High Dimensions via Neural Exploration-Exploitation Trees
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 |
|---|---|---|---|
| Replace guided progressive expansion with breadth-first expansion, retaining NEXT-KS's learned sampling policy (ablation) | NEXT-KS · planning benchmarks | success rate | Hurt |
| Replace guided progressive expansion with breadth-first expansion, retaining NEXT-KS's learned sampling policy (ablation) | NEXT-KS · planning benchmarks | collision checks | Hurt |
| Replace the attention-based neural architecture with improved GPPN (ablation) | NEXT · high-dimensional planning benchmarks | success rate | Hurt |
| Replace the attention-based neural architecture with improved GPPN (ablation) | NEXT · high-dimensional planning benchmarks | path cost | Hurt |
| Replace the learned policy and value networks with a workspace Dijkstra heuristic (ablation) | NEXT · planning tasks above 2d | planning performance | Hurt |
| Use a workspace Dijkstra heuristic instead of learned guidance (ablation) | NEXT · 2d workspace planning | planning performance | No clear effect |
| Learn value and policy from accumulated successful planning experiences (MSIL) | NEXT · 5d 3-link snake | collision checks: one-twentieth of its samples | Helped |
Closest papers by meaning
- System 1.x: Learning to Balance Fast and Slow Planning with Language Models (ICLR 2025 · similarity 0.86)
- Learning Domain-Independent Heuristics for Grounded and Lifted Planning (AAAI 2024 · similarity 0.86)
- Tree-Guided Diffusion Planner (NeurIPS 2025 · similarity 0.85)
- Compositional Monte Carlo Tree Diffusion for Extendable Planning (NeurIPS 2025 · similarity 0.84)
- Decoupling Exploration and Policy Optimization: Uncertainty Guided Tree Search for Hard Exploration (NeurIPS 2026 · similarity 0.84)
- Graph Sparse Sampling: Breaking the Curse of the Horizon in Continuous MDP Planning (NeurIPS 2026 · similarity 0.84)
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.