Score: 0

Parallelizing Tree Search with Twice Sequential Monte Carlo

Published: November 18, 2025 | arXiv ID: 2511.14220v1

By: Yaniv Oren , Joery A. de Vries , Pascal R. van der Vaart and more

Potential Business Impact:

Makes AI learn faster and better.

Business Areas:
A/B Testing Data and Analytics

Model-based reinforcement learning (RL) methods that leverage search are responsible for many milestone breakthroughs in RL. Sequential Monte Carlo (SMC) recently emerged as an alternative to the Monte Carlo Tree Search (MCTS) algorithm which drove these breakthroughs. SMC is easier to parallelize and more suitable to GPU acceleration. However, it also suffers from large variance and path degeneracy which prevent it from scaling well with increased search depth, i.e., increased sequential compute. To address these problems, we introduce Twice Sequential Monte Carlo Tree Search (TSMCTS). Across discrete and continuous environments TSMCTS outperforms the SMC baseline as well as a popular modern version of MCTS. Through variance reduction and mitigation of path degeneracy, TSMCTS scales favorably with sequential compute while retaining the properties that make SMC natural to parallelize.

Country of Origin
🇳🇱 Netherlands

Page Count
21 pages

Category
Computer Science:
Machine Learning (CS)