SC2Tools: StarCraft II Toolset and Dataset API

• URL: http://arxiv.org/abs/2509.18454v1
• Date: Mon, 22 Sep 2025 22:25:21 GMT
• Title: SC2Tools: StarCraft II Toolset and Dataset API
• Authors: Andrzej Białecki, Piotr Białecki, Piotr Sowiński, Mateusz Budziak, Jan Gajewski,
• Abstract summary: Gaming and esports are key areas influenced by the application of Artificial Intelligence (AI) and Machine Learning (ML) solutions at scale.<n>In this work, we present SC2Tools'', a toolset containing multiple submodules responsible for working with, and producing larger datasets.<n>The tools we present were leveraged in creating one of the largest StarCraft2 tournament datasets to date with a separate PyTorch and PyTorch application Lightning programming interface (API) for easy access to the data.
• Score: 0.26097841018267615
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Computer games, as fully controlled simulated environments, have been utilized in significant scientific studies demonstrating the application of Reinforcement Learning (RL). Gaming and esports are key areas influenced by the application of Artificial Intelligence (AI) and Machine Learning (ML) solutions at scale. Tooling simplifies scientific workloads and is essential for developing the gaming and esports research area. In this work, we present ``SC2Tools'', a toolset containing multiple submodules responsible for working with, and producing larger datasets. We provide a modular structure of the implemented tooling, leaving room for future extensions where needed. Additionally, some of the tools are not StarCraft~2 exclusive and can be used with other types of data for dataset creation. The tools we present were leveraged in creating one of the largest StarCraft~2 tournament datasets to date with a separate PyTorch and PyTorch Lightning application programming interface (API) for easy access to the data. We conclude that alleviating the burden of data collection, preprocessing, and custom code development is essential for less technically proficient researchers to engage in the growing gaming and esports research area. Finally, our solution provides some foundational work toward normalizing experiment workflow in StarCraft~2

Related papers

• Transductive Visual Programming: Evolving Tool Libraries from Experience for Spatial Reasoning [63.071280297939005]
  We present Transductive Visual Programming (TVP), a novel framework that builds new tools from its own experience rather than speculation.<n>TVP achieves state-of-the-art performance, outperforming GPT-4o by 22% and the previous best visual programming system by 11%.<n>Our work establishes experience-driven transductive tool creation as a powerful paradigm for building self-evolving visual programming agents.
  arXiv  Detail & Related papers  (2025-12-24T04:30:21Z)
• Code4MeV2: a Research-oriented Code-completion Platform [3.552490023407639]
  We introduce Code4MeV2, a research-oriented, open-source code completion plugin for JetBrains IDEs.<n>Code4MeV2 is designed using a client--server architecture and features inline code completion and a context-aware chat assistant.<n>It achieves industry-comparable performance in terms of code completion, with an average latency of 200ms.
  arXiv  Detail & Related papers  (2025-10-04T09:40:43Z)
• SEART Data Hub: Streamlining Large-Scale Source Code Mining and Pre-Processing [13.717170962455526]
  We present the SEART Data Hub, a web application that allows to easily build and pre-process large-scale datasets featuring code mined from public GitHub repositories. Through a simple web interface, researchers can specify a set of mining criteria as well as specific pre-processing steps they want to perform. After submitting the request, the user will receive an email with a download link for the required dataset within a few hours.
  arXiv  Detail & Related papers  (2024-09-27T11:42:19Z)
• Cradle: Empowering Foundation Agents Towards General Computer Control [80.02794667853045]
  We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Cradle can understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning. Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games, five software applications, and a comprehensive benchmark, OSWorld.
  arXiv  Detail & Related papers  (2024-03-05T18:22:29Z)
• AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning [38.75717733273262]
  StarCraft II is one of the most challenging simulated reinforcement learning environments. Blizzard has released a massive dataset of millions of StarCraft II games played by human players. We define a dataset (a subset of Blizzard's release), tools standardizing an API for machine learning methods, and an evaluation protocol.
  arXiv  Detail & Related papers  (2023-08-07T12:21:37Z)
• Technical Challenges of Deploying Reinforcement Learning Agents for Game Testing in AAA Games [58.720142291102135]
  We describe an effort to add an experimental reinforcement learning system to an existing automated game testing solution based on scripted bots. We show a use-case of leveraging reinforcement learning in game production and cover some of the largest time sinks anyone who wants to make the same journey for their game may encounter. We propose a few research directions that we believe will be valuable and necessary for making machine learning, and especially reinforcement learning, an effective tool in game production.
  arXiv  Detail & Related papers  (2023-07-19T18:19:23Z)
• CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models [74.22729793816451]
  Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability. We propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math competition problems.
  arXiv  Detail & Related papers  (2023-05-23T17:51:52Z)
• Nerfstudio: A Modular Framework for Neural Radiance Field Development [60.210943944285184]
  Nerfstudio is a modular PyTorch framework for implementing Neural Radiance Fields (NeRF) methods. NeRF is a rapidly growing area of research with wide-ranging applications in computer vision, graphics, robotics, and more. Our framework includes plug-and-play components for implementing NeRF-based methods, which make it easy for researchers and practitioners to incorporate NeRF into their projects.
  arXiv  Detail & Related papers  (2023-02-08T18:58:00Z)
• The Open MatSci ML Toolkit: A Flexible Framework for Machine Learning in Materials Science [3.577720074630756]
  The Open MatSci ML Toolkit is a flexible, self-contained, and scalable Python-based framework to apply deep learning models and methods on scientific data. By publishing and sharing this toolkit with the research community via open-source release, we hope to:. Lower the entry barrier for new machine learning researchers and practitioners that want to get started with the OpenCatalyst dataset.
  arXiv  Detail & Related papers  (2022-10-31T17:11:36Z)
• SC2EGSet: StarCraft II Esport Replay and Game-state Dataset [0.0]
  This work aims to open esports to a broader scientific community by supplying raw and pre-processed files from StarCraft II esports tournaments. We have publicly available game-engine generated "replays" of tournament matches and performed data extraction using a low-level application programming interface (API) library. Our dataset contains replays from major and premiere StarCraft II tournaments since 2016.
  arXiv  Detail & Related papers  (2022-07-07T16:52:53Z)
• Applying supervised and reinforcement learning methods to create neural-network-based agents for playing StarCraft II [0.0]
  We propose a neural network architecture for playing the full two-player match of StarCraft II trained with general-purpose supervised and reinforcement learning. Our implementation achieves a non-trivial performance when compared to the in-game scripted bots.
  arXiv  Detail & Related papers  (2021-09-26T20:08:10Z)
• OpenHoldem: An Open Toolkit for Large-Scale Imperfect-Information Game Research [82.09426894653237]
  OpenHoldem is an integrated toolkit for large-scale imperfect-information game research using NLTH. OpenHoldem makes three main contributions to this research direction: 1) a standardized evaluation protocol for thoroughly evaluating different NLTH AIs, 2) three publicly available strong baselines for NLTH AI, and 3) an online testing platform with easy-to-use APIs for public NLTH AI evaluation.
  arXiv  Detail & Related papers  (2020-12-11T07:24:08Z)
• MSC: A Dataset for Macro-Management in StarCraft II [52.52008929278214]
  We release a new macro-management dataset based on the platform SC2LE. MSC consists of well-designed feature vectors, pre-defined high-level actions and final result of each match. Besides the dataset, we propose a baseline model and present initial baseline results for global state evaluation and build order prediction.
  arXiv  Detail & Related papers  (2017-10-09T14:59:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.