Research map / Learning theory and algorithms / Combinatorial and search optimization
Watch the Unobserved: A Simple Approach to Parallelizing 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 |
|---|---|---|---|
| Track in-progress rollouts as unobserved samples and add their counts to the UCT exploration term | parallel MCTS · Atari Games | average episode return: 49% | Helped |
| Track in-progress rollouts as unobserved samples and add their counts to the UCT exploration term | parallel MCTS · Atari Games | average episode return: 104% | Helped |
| Track in-progress rollouts as unobserved samples and add their counts to the UCT exploration term | parallel MCTS · Atari Games | average episode return: 82% | Helped |
| Increase the number of expansion and simulation workers | WU-UCT · Joy City Level-35 and Level-58 | speedup: 15.5; 20.9 | Helped |
| Increase the number of parallel workers | WU-UCT · Joy City Level-35 and Level-58 | average game steps: 0.67; 1.22 | No clear effect |
| Use WU-UCT for user pass-rate prediction | Joy City pass-rate prediction system · 130 released game-levels | MAE: 8.6% | Helped |
Closest papers by meaning
- Speculative Monte-Carlo Tree Search (NeurIPS 2024 · similarity 0.88)
- Monte Carlo Tree Search in the Presence of Transition Uncertainty (AAAI 2024 · similarity 0.87)
- Graph-Based Stochastic-Power-UCT: Monte-Carlo Graph Search with Power Mean Estimation (NeurIPS 2026 · similarity 0.86)
- Monte-Carlo Tree Search with Uncertainty Propagation via Optimal Transport (ICML 2025 · similarity 0.86)
- Fast Monte Carlo Tree Diffusion: 100× Speedup via Parallel and Sparse Planning (NeurIPS 2025 · similarity 0.85)
- An Efficient Algorithm for Thresholding Monte Carlo Tree Search (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.