# Array-Based Monte Carlo Tree Search

arXiv: https://arxiv.org/abs/2508.20140 · HTML: https://mlsanity.com/paper/2508.20140/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 24 references that are in the map.
- First posted on arXiv 27 Aug 2025.

## Builds on (most cited first, 4 of 4)

- [Monte Carlo Tree Search: A Review of Recent Modifications and Applications](https://mlsanity.com/paper/2103.04931/) (2021)
- [HyP-DESPOT: A Hybrid Parallel Algorithm for Online Planning under Uncertainty](https://mlsanity.com/paper/1802.06215/) (2018)
- [Neural Tree Expansion for Multi-Robot Planning in Non-Cooperative Environments](https://mlsanity.com/paper/2104.09705/) (2021)
- [Monte Carlo Tree Search with Spectral Expansion for Planning with Dynamical Systems](https://mlsanity.com/paper/2412.11270/) (2024)

## Abstract (arXiv)

Monte Carlo Tree Search is a popular method for solving decision making problems. Faster implementations allow for more simulations within the same wall clock time, directly improving search performance. To this end, we present an alternative array-based implementation of the classic Upper Confidence bounds applied to Trees algorithm. Our method preserves the logic of the original algorithm, but eliminates the need for branch prediction, enabling faster performance on pipelined processors, and up to a factor of 2.8 times better scaling with search depth in our numerical simulations.