# Batch Monte Carlo Tree Search

arXiv: https://arxiv.org/abs/2104.04278 · HTML: https://mlsanity.com/paper/2104.04278/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 28 references that are in the map.
- First posted on arXiv 9 Apr 2021.

## Builds on (most cited first, 6 of 6)

- [Accelerating Self-Play Learning in Go](https://mlsanity.com/paper/1902.10565/) (2019)
- [ELF OpenGo: An Analysis and Open Reimplementation of AlphaZero](https://mlsanity.com/paper/1902.04522/) (2019)
- [Watch the Unobserved: A Simple Approach to Parallelizing Monte Carlo Tree Search](https://mlsanity.com/paper/1810.11755/) (2018)
- [Polygames: Improved Zero Learning](https://mlsanity.com/paper/2001.09832/) (2020)
- [Mobile Networks for Computer Go](https://mlsanity.com/paper/2008.10080/) (2020)
- [Improving Model and Search for Computer Go](https://mlsanity.com/paper/2102.03467/) (2021)

## Built on by (most cited first, 5 of 5)

- [Vision Transformers for Computer Go](https://mlsanity.com/paper/2309.12675/) (2023)
- [Enhancing Reinforcement Learning Through Guided Search](https://mlsanity.com/paper/2408.10113/) (2024)
- [Earth Observation Satellite Scheduling with Graph Neural Networks and Monte Carlo Tree Search](https://mlsanity.com/paper/2408.15041/) (2024)
- [Rapfi: Distilling Efficient Neural Network for the Game of Gomoku](https://mlsanity.com/paper/2503.13178/) (2025)
- [Particle Monte Carlo Tree Search](https://mlsanity.com/paper/2605.08982/) (2026)

## Abstract (arXiv)

Making inferences with a deep neural network on a batch of states is much faster with a GPU than making inferences on one state after another. We build on this property to propose Monte Carlo Tree Search algorithms using batched inferences. Instead of using either a search tree or a transposition table we propose to use both in the same algorithm. The transposition table contains the results of the inferences while the search tree contains the statistics of Monte Carlo Tree Search. We also propose to analyze multiple heuristics that improve the search: the μ FPU, the Virtual Mean, the Last Iteration and the Second Move heuristics. They are evaluated for the game of Go using a MobileNet neural network.