Skip to content

[PR] Generate Paper Pull Request Fix #10

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Kaszanas merged 2 commits into from
Feb 18, 2026
Merged

[PR] Generate Paper Pull Request Fix #10

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
1b92453
Adjusted summary as per review
Kaszanas Feb 17, 2026
d356b85
enumeration follows sections
Kaszanas Feb 17, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 2 additions & 4 deletions paper.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,9 +47,7 @@ bibliography: ./article/paper.bib

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.
In this work, we present "SC2Tools", a toolset containing multiple submodules responsible for working with, and producing larger datasets. StarCraft~2 is a known real-time strategy game (RTS) and one of the long-standing esports titles. 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. We provide 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

Expand All @@ -70,7 +68,7 @@ So far, our software was leveraged in preparation of major datasets: "SC2ReSet"

# Software Description

Our software consists of multiple modules that the user can match to their specific needs. To easily extend our toolset, the main repository of "SC2Tools" contains multiple git submodules. Each submodule is a separate repository with the logic required to perform a specific tasks on the SC2Replay files. The full pipeline in a simplified pictorial form is showcased in \autoref{fig:DatasetPipeline}. The motivation for this structure is twofold. Firstly, it makes evolving the toolset easier, as modules can be easily replaced, or new ones added. Secondly, users have the option of using only a portion of the pipeline. The full list of current submodules is as follows: (1) "SC2InfoExtractorGo" [@Bialecki_2021_SC2InfoExtractorGo], (2) "DatasetPreparator" [@Bialecki_2022_SC2DatasetPreparator], (3) "SC2AnonServerPy" [@Bialecki_2021_SC2AnonServerPy]. (4) "SC2_Datasets" [@bialecki_2022_sc2datasets].
Our software consists of multiple modules that the user can match to their specific needs. To easily extend our toolset, the main repository of "SC2Tools" contains multiple git submodules. Each submodule is a separate repository with the logic required to perform a specific tasks on the SC2Replay files. The full pipeline in a simplified pictorial form is showcased in \autoref{fig:DatasetPipeline}. The motivation for this structure is twofold. Firstly, it makes evolving the toolset easier, as modules can be easily replaced, or new ones added. Secondly, users have the option of using only a portion of the pipeline. The full list of current submodules is as follows: (1) "DatasetPreparator" [@Bialecki_2022_SC2DatasetPreparator], (2) "SC2InfoExtractorGo" [@Bialecki_2021_SC2InfoExtractorGo], (3) "SC2AnonServerPy" [@Bialecki_2021_SC2AnonServerPy]. (4) "SC2_Datasets" [@bialecki_2022_sc2datasets].

![Simplified full pipeline using SC2Tools to create two datasets, "SC2ReSet" [@Bialecki2022ReSetZenodo] and "SC2EGSet" Dataset [@Bialecki2023EGSetZenodo]. Initially introduced in [@Bialecki2023SC2EGSet]. \label{fig:DatasetPipeline}](./article/SC2Tools_Pipeline_Complete.pdf)

Expand Down