Research map / Probabilistic and scientific modeling / Bayesian optimization
Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search
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 |
|---|---|---|---|
| add LA-MCTS learned space partition on top of TuRBO | TuRBO · MuJoCo locomotion tasks (6 tasks) | reward vs samples | Helped |
| add LA-MCTS partitioning on top of BO and TuRBO | BO / TuRBO · Ackley and Rosenbrock, 20d and 100d | objective value | Helped |
| use LA-MCTS (black-box) instead of gradient-based methods | LA-MCTS · MuJoCo high-dimensional tasks (Walker2d, Ant, Humanoid) | samples to reach reward threshold | Hurt |
| use LA-MCTS instead of NG and TRPO on simple tasks | LA-MCTS · Swimmer-v2 | episodes to threshold: 126 vs 427 (ARS), 1450 (NG-lin) | Helped |
| set exploration constant Cp to zero or too small (pure greedy) instead of moderate (ablation) | LA-MCTS · HalfCheetah | reward | Hurt |
| use very large Cp (over-exploration) (ablation) | LA-MCTS · HalfCheetah | reward | Hurt |
| use nonlinear SVM kernel (polynomial/RBF) instead of linear (ablation) | LA-MCTS · HalfCheetah | reward | Helped |
| reduce splitting threshold theta to 2 from 10 (ablation) | LA-MCTS · HalfCheetah | reward | Hurt |
Closest papers by meaning
- Monte Carlo Tree Descent for Black-Box Optimization (NeurIPS 2022 · similarity 0.91)
- Monte Carlo Tree Search based Space Transfer for Black Box Optimization (NeurIPS 2024 · similarity 0.90)
- Adaptive Partitioning Schemes for Optimistic Optimization (ICML 2025 · similarity 0.86)
- BBOWP-Bench: Evaluating LLMs on Black-Box Optimization Word Problems (NeurIPS 2026 · similarity 0.85)
- Posterior Inference with Diffusion Models for High-dimensional Black-box Optimization (ICML 2025 · similarity 0.85)
- Kernel Learning for Sample Constrained Black-Box Optimization (AAAI 2025 · 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.