arXiv cs.AI· Emanuel Dopater, Daniel Gavlas, Luk\'a\v{s} Jochymek, Kannan Paul, Miloslav Szczypka, David Voj\'a\v{c}ek, Josef \v{Z}\'a\v{c}ek, Jan Plucar, Radek Svoboda, Ivan Zelinka·· 2 小时前AI 评分28
基于《Counter-Strike 2》高频交互数据迈向快速人类反应建模
Toward Fast Human Reaction Modeling from High-Frequency Digital Interaction Data
AI 导读
一项探索性研究在《Counter-Strike 2》毫秒级高精度遥测数据中识别快速、显著性驱动的行为特征，提出 Ego-Knowledge 感知状态重建方法与 60–120 ms 反应窗口，并训练出 EMBER（梯度提升）和 ORBIT（自定义 Transformer）两个模型。
正文 · 原文
Abstract:We investigate whether limbic-like signatures of rapid, salience-driven behavior can be identified in high-resolution Counter-Strike 2 telemetry. This exploratory study introduces Ego-Knowledge, a leak-reduced reconstruction of each player's plausible perceptual state, supported by a millisecond-precision visibility engine and a reaction-centered extraction pipeline. Using a neuroscience-motivated 60--120 ms window, we derive coarse fight-or-flight labels from visibility- and damage-triggered events, with back-damage cases enabling constrained reaction-time analysis and manual label checks. We train two telemetry-native models using only information available by the trigger: EMBER (gradient boosting) and ORBIT (a custom transformer). On the full validation set, EMBER achieves 73.5% accuracy and ORBIT 71.2%, versus a 51.5% majority-class baseline, and both generalize to held-out players. The strongest LLM baseline achieves 62.7% on 1,000 validation cases; on these same cases, EMBER (73.6%) and ORBIT (70.9%) perform better (McNemar p=1.3e-9 and 1.5e-6, respectively), with orders-of-magnitude lower inference time and cost, though the comparison is not compute-matched. Including a short post-trigger window changes forecasting into early response recognition, raising accuracy monotonically to 85.15%. We propose this curve as a candidate probe of the transition from rapid to deliberative control, but roughly uniform per-tick gains do not establish that interpretation. The neuroscience framing is hypothesis-generating, not mechanistic: physiological ground truth, suitable control distributions, and reverse-inference limitations remain open. We outline extensions to auditory reconstruction, larger datasets, and telemetry-native foundation models.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.35079 [cs.AI] |
| (or arXiv:2610.35079v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35079 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Radek Svoboda [view email]
[v1]
Mon, 26 Oct 2026 09:24:10 UTC (2,482 KB)
来源：arXiv cs.AI · arxiv.org