Scholarlink

Background <p>Early childhood mathematics learning benefits from adaptive technologies; however, effective real-time personalisation remains a challenge. However, prior models often rely on static difficulty or rule-based adaptation, with limited evidence in preschool-aged children. This study asks whether a multimodal deep reinforcement learning (DRL) model can outperform rule-based adaptation in personalising preschool math tasks.</p> Methods <p>A total of 84 children aged 4–6 participated in a controlled trial comparing DRL personalisation to rule-based adaptation. The DRL system incorporated multimodal inputs (click latency, hesitation, facial affect) and was trained via a Deep Q-Network on a Dell server with GPU acceleration. Performance, engagement, and mastery outcomes were analysed using mixed-effects ANOVA and benchmarked against established adaptive models.</p> Results <p>DRL users improved EMAS scores by + 12.7 points versus + 6.8 in controls (<i>p</i> = 0.001), achieved 84.2% task accuracy compared to 76.3% (<i>p</i> &lt; 0.001), and reduced response latency from 2.61&#xa0;s to 1.91&#xa0;s (<i>p</i> &lt; 0.001). Level 3 mastery reached 69.0% versus 40.5% (<i>p</i> = 0.007). Hesitation frequency was lower (0.18 vs. 0.29 per task), joy expression higher (0.36 vs. 0.27 AU rate), and dropout flags fewer (3.1% vs. 8.9%), all <i>p</i> &lt; 0.001. External comparisons confirmed superior accuracy, stability of engagement, and fidelity of execution.</p> Conclusion <p>Multimodal DRL significantly enhances early math learning, supporting both technical personalisation and meaningful educational gains in preschool settings.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Design and evaluation of personalised early childhood mathematics enlightenment games based on deep reinforcement learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月20日

查看全文
  • Lin Wang

摘要

Background

Early childhood mathematics learning benefits from adaptive technologies; however, effective real-time personalisation remains a challenge. However, prior models often rely on static difficulty or rule-based adaptation, with limited evidence in preschool-aged children. This study asks whether a multimodal deep reinforcement learning (DRL) model can outperform rule-based adaptation in personalising preschool math tasks.

Methods

A total of 84 children aged 4–6 participated in a controlled trial comparing DRL personalisation to rule-based adaptation. The DRL system incorporated multimodal inputs (click latency, hesitation, facial affect) and was trained via a Deep Q-Network on a Dell server with GPU acceleration. Performance, engagement, and mastery outcomes were analysed using mixed-effects ANOVA and benchmarked against established adaptive models.

Results

DRL users improved EMAS scores by + 12.7 points versus + 6.8 in controls (p = 0.001), achieved 84.2% task accuracy compared to 76.3% (p < 0.001), and reduced response latency from 2.61 s to 1.91 s (p < 0.001). Level 3 mastery reached 69.0% versus 40.5% (p = 0.007). Hesitation frequency was lower (0.18 vs. 0.29 per task), joy expression higher (0.36 vs. 0.27 AU rate), and dropout flags fewer (3.1% vs. 8.9%), all p < 0.001. External comparisons confirmed superior accuracy, stability of engagement, and fidelity of execution.

Conclusion

Multimodal DRL significantly enhances early math learning, supporting both technical personalisation and meaningful educational gains in preschool settings.