Warsaw University of Technology, Electronics and Information Technology, Warsaw, Poland.
SWPS University, Neurocognitive Research Center, Warsaw, Poland.
Sci Data. 2023 Sep 8;10(1):600. doi: 10.1038/s41597-023-02510-7.
As a relatively new form of sport, esports offers unparalleled data availability. Our work aims to open esports to a broader scientific community by supplying raw and pre-processed files from StarCraft II esports tournaments. These files can be used in statistical and machine learning modeling tasks and compared to laboratory-based measurements. Additionally, we open-sourced and published all the custom tools that were developed in the process of creating our dataset. These tools include PyTorch and PyTorch Lightning API abstractions to load and model the data. Our dataset contains replays from major and premiere StarCraft II tournaments since 2016. We processed 55 "replaypacks" that contained 17930 files with game-state information. Our dataset is one of the few large publicly available sources of StarCraft II data upon its publication. Analysis of the extracted data holds promise for further Artificial Intelligence (AI), Machine Learning (ML), psychological, Human-Computer Interaction (HCI), and sports-related studies in a variety of supervised and self-supervised tasks.
作为一种相对较新的运动形式，电子竞技提供了无与伦比的数据可用性。我们的工作旨在通过提供星际争霸 II 电子竞技比赛的原始和预处理文件，将电子竞技开放给更广泛的科学界。这些文件可用于统计和机器学习建模任务，并与基于实验室的测量进行比较。此外，我们开源并发布了在创建数据集过程中开发的所有自定义工具。这些工具包括用于加载和建模数据的 PyTorch 和 PyTorch Lightning API 抽象。我们的数据集包含自 2016 年以来主要和首屈一指的星际争霸 II 锦标赛的重播。我们处理了 55 个“重播包”，其中包含 17930 个带有游戏状态信息的文件。在发布时，我们的数据集是少数几个大型公开可用的星际争霸 II 数据来源之一。对提取数据的分析有望在各种监督和自我监督任务中为人工智能 (AI)、机器学习 (ML)、心理学、人机交互 (HCI) 和与运动相关的研究提供帮助。
