EnMatch: Matchmaking for Better Player Engagement via Neural Combinatorial Optimization

Authors: Kai Wang, Haoyu Liu, Zhipeng Hu, Xiaochuan Feng, Minghao Zhao, Shiwei Zhao, Runze Wu, Xudong Shen, Tangjie Lv, Changjie Fan

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The performance of En Match is finally demonstrated through the comparison with other state-of-the-art methods based on several real-world datasets and online deployments on two games.
Researcher Affiliation Industry Fuxi AI Lab, Net Ease Inc., Hangzhou, China {wangkai02,liuhaoyu03,zphu,fengxiaochuan,zhaominghao,zhaoshiwei,wurunze1, hzshenxudong,hzlvtangjie,fanchangjie}@corp.netease.com
Pseudocode Yes The algorithm is elaborately described in Algorithm 1 located in the Appendix.
Open Source Code No The paper does not provide an explicit statement or link for the release of its source code.
Open Datasets No The paper mentions using "SPG dataset" and "RG PVP dataset" which are described as industrial datasets, but no concrete access information (link, DOI, citation with authors/year) is provided for public availability.
Dataset Splits No The paper states "More experiment details, including data process, data split, feature design, hyperparameters, and simulation process are listed in the Appendix." However, it does not provide specific split percentages or counts in the main text, nor does it cite predefined splits with access information.
Hardware Specification Yes For all the experiments, we are using a single Ge Force GTX 2080 Ti GPU, 8CPU, and 64GB memory.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup No The paper states "More experiment details, including data process, data split, feature design, hyperparameters, and simulation process are listed in the Appendix." However, it does not provide specific hyperparameter values or training configurations in the main text.