Research map / Learning theory and algorithms / Combinatorial and search optimization
Monte-Carlo Tree Search by Best Arm Identification
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 |
|---|---|---|---|
| Use LUCB-MCTS instead of FindTopWinner | Depth-two benchmark tree · Depth-two benchmark tree | samples: 17097 -> 2460 | Helped |
| Use UGapE-MCTS instead of FindTopWinner | Depth-two benchmark tree · Depth-two benchmark tree | samples: 17097 -> 2419 | Helped |
| Use LUCB-MCTS instead of M-LUCB | Depth-two benchmark tree · Depth-two benchmark tree | samples: 2399 -> 2460 | Hurt |
| Use UGapE-MCTS instead of M-LUCB | Depth-two benchmark tree · Depth-two benchmark tree | samples: 2399 -> 2419 | Hurt |
| Use LUCB-MCTS instead of FindTopWinner | Depth-three 3-way tree · Depth-three 3-way tree | samples: 20730 -> 1551 | Helped |
| Use UGapE-MCTS instead of FindTopWinner | Depth-three 3-way tree · Depth-three 3-way tree | samples: 20730 -> 1584 | Helped |
| Use LUCB-MCTS instead of FindTopWinner | 10K full 10-ary trees of depth 3 · 10K full 10-ary trees of depth 3 | average samples: 2254560 -> 141811 | Helped |
| Use UGapE-MCTS instead of FindTopWinner | 10K full 10-ary trees of depth 3 · 10K full 10-ary trees of depth 3 | average samples: 2254560 -> 142953 | Helped |
| Use global-time confidence intervals beta(t, delta) instead of local-draw intervals beta(N_l(t), delta) (ablation) | BAI-MCTS · Monte-Carlo tree search | number of play-outs | No clear effect |
Closest papers by meaning
- An Efficient Algorithm for Thresholding Monte Carlo Tree Search (NeurIPS 2026 · similarity 0.91)
- $\epsilon$-Good Action Identification in Fixed-Budget Monte Carlo Tree Search (NeurIPS 2026 · similarity 0.90)
- Bilevel MCTS for Amortized O(1) Node Selection in Classical Planning (AAAI 2026 · similarity 0.88)
- Thompson Sampling for Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit (AAAI 2024 · similarity 0.87)
- Online Robust Reinforcement Learning Through Monte-Carlo Planning (ICML 2025 · similarity 0.87)
- Near Optimal Best Arm Identification for Clustered Bandits (ICML 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.