arXiv cs.AI· Tobias Schneider, Lorenz Sparrenberg, Priya Tomar, Shahzeb Qamar, Tobias Deu{\ss}er, Rafet Sifa·· 12 小时前AI 评分20
PlayerEmbed：从原始输入序列学习玩家行为指纹表征
PlayerEmbed: Learning Behavioral Fingerprint Representations from Raw Input Sequences
AI 导读
PlayerEmbed 框架用深度度量学习从原始游戏输入序列中学习紧凑的玩家嵌入向量，编码器为 CNN-LSTM 混合结构，训练数据来自 1,000 名玩家。基于参考嵌入构建的最近质心分类器在训练中见过的玩家上达到 0.950 平衡准确率，在训练中完全未见的 1,000 名玩家上达到 0.879。
正文 · 原文
Abstract:Raw player input sequences in video games contain fine-grained behavior, but are high-dimensional and noisy, which makes large-scale analytics challenging. To address this, we introduce PlayerEmbed, a framework that learns compact and discriminative player embeddings using deep metric learning. Our approach uses a hybrid CNN-LSTM encoder trained on raw input sequences from 1,000 players. We evaluate the model on held-out sequences from these players and on sequences from 1,000 players entirely unseen during training to assess generalization to unseen identities. For player identification, a nearest-centroid classifier built from reference embeddings achieves strong performance, reaching balanced accuracies of 0.950 for players seen during training and 0.879 for players unseen during training. Systematically increasing the number of training players substantially improves generalization to unseen players, indicating a transition from simple fingerprinting to learning transferable behavioral patterns.
| Comments: | Accepted at IEEE DSAA 2026 |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.32727 [cs.LG] |
| (or arXiv:2610.32727v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.32727 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tobias Schneider [view email]
[v1]
Fri, 23 Oct 2026 14:48:02 UTC (280 KB)
来源：arXiv cs.AI · arxiv.org