Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Ye, Zhu, Mengran, Gui, Kailin, Yu, Jiayue, Hao, Yong, Sun, Haozhan
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2403.10720
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913267109068800
author Zhang, Ye
Zhu, Mengran
Gui, Kailin
Yu, Jiayue
Hao, Yong
Sun, Haozhan
author_facet Zhang, Ye
Zhu, Mengran
Gui, Kailin
Yu, Jiayue
Hao, Yong
Sun, Haozhan
contents In this study, we explore the efficiency of the Monte Carlo Tree Search (MCTS), a prominent decision-making algorithm renowned for its effectiveness in complex decision environments, contingent upon the volume of simulations conducted. Notwithstanding its broad applicability, the algorithm's performance can be adversely impacted in certain scenarios, particularly within the domain of game strategy development. This research posits that the inherent branch divergence within the Da Vinci Code board game significantly impedes parallelism when executed on Graphics Processing Units (GPUs). To investigate this hypothesis, we implemented and meticulously evaluated two variants of the MCTS algorithm, specifically designed to assess the impact of branch divergence on computational performance. Our comparative analysis reveals a linear improvement in performance with the CPU-based implementation, in stark contrast to the GPU implementation, which exhibits a non-linear enhancement pattern and discernible performance troughs. These findings contribute to a deeper understanding of the MCTS algorithm's behavior in divergent branch scenarios, highlighting critical considerations for optimizing game strategy algorithms on parallel computing architectures.
format Preprint
id arxiv_https___arxiv_org_abs_2403_10720
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Development and Application of a Monte Carlo Tree Search Algorithm for Simulating Da Vinci Code Game Strategies
Zhang, Ye
Zhu, Mengran
Gui, Kailin
Yu, Jiayue
Hao, Yong
Sun, Haozhan
Artificial Intelligence
In this study, we explore the efficiency of the Monte Carlo Tree Search (MCTS), a prominent decision-making algorithm renowned for its effectiveness in complex decision environments, contingent upon the volume of simulations conducted. Notwithstanding its broad applicability, the algorithm's performance can be adversely impacted in certain scenarios, particularly within the domain of game strategy development. This research posits that the inherent branch divergence within the Da Vinci Code board game significantly impedes parallelism when executed on Graphics Processing Units (GPUs). To investigate this hypothesis, we implemented and meticulously evaluated two variants of the MCTS algorithm, specifically designed to assess the impact of branch divergence on computational performance. Our comparative analysis reveals a linear improvement in performance with the CPU-based implementation, in stark contrast to the GPU implementation, which exhibits a non-linear enhancement pattern and discernible performance troughs. These findings contribute to a deeper understanding of the MCTS algorithm's behavior in divergent branch scenarios, highlighting critical considerations for optimizing game strategy algorithms on parallel computing architectures.
title Development and Application of a Monte Carlo Tree Search Algorithm for Simulating Da Vinci Code Game Strategies
topic Artificial Intelligence
url https://arxiv.org/abs/2403.10720