Feature selection is critical for improving the performance and interpretability of machine learning models, particularly in high-dimensional spaces where complex feature interactions can reduce accuracy and increase computational demands. Existing approaches often rely on static feature subsets or manual intervention, limiting adaptability and scalability. However, dynamic, per-instance feature selection methods and model-specific interpretability in reinforcement learning remain underexplored. This study proposes a human-in-the-loop (HITL) feature selection framework integrated into a Double Deep Q-Network (DDQN) using a Kolmogorov-Arnold Network (KAN). Our novel approach leverages simulated human feedback and stochastic distribution-based sampling, specifically Beta, to iteratively refine feature subsets per data instance, improving flexibility in feature selection. The KAN-DDQN achieved notable test accuracies of 93% on MNIST and 83% on FashionMNIST, outperforming conventional MLP-DDQN models by up to 9%. The KAN-based model provided high interpretability via symbolic representation while using 4 times fewer neurons in the hidden layer than MLPs did. Comparatively, the models without feature selection achieved test accuracies of only 58% on MNIST and 64% on FashionMNIST, highlighting significant gains with our framework. We further validate scalability on CIFAR-10 and CIFAR-100, achieving up to 30% relative macro F1 improvement on MNIST and 5% on CIFAR-10, while reducing calibration error by 25%. Complexity analysis confirms real-time feasibility with latency below 1 ms and parameter counts under 0.02M. Pruning and visualization further enhanced model transparency by elucidating decision pathways. These findings present a scalable, interpretable solution for feature selection that is suitable for applications requiring real-time, adaptive decision-making with minimal human oversight.

翻译：特征选择对于提升机器学习模型的性能与可解释性至关重要，尤其是在高维空间中，复杂的特征交互会降低模型精度并增加计算负担。现有方法通常依赖于静态特征子集或人工干预，限制了其适应性与可扩展性。然而，面向强化学习的动态实例级特征选择方法及模型特异性可解释性研究仍显不足。本研究提出一种融合人机协同（HITL）机制的特征选择框架，该框架基于Kolmogorov-Arnold网络（KAN）集成至双深度Q网络（DDQN）中。我们提出的创新方法利用模拟人类反馈和基于随机分布（特别是Beta分布）的采样技术，针对每个数据实例迭代优化特征子集，从而提升特征选择的灵活性。KAN-DDQN在MNIST和FashionMNIST数据集上分别取得了93%和83%的测试准确率，较传统MLP-DDQN模型提升最高达9%。基于KAN的模型通过符号表示提供了高可解释性，且其隐藏层神经元数量仅为MLP模型的四分之一。相比之下，未采用特征选择的模型在MNIST和FashionMNIST上的测试准确率分别仅为58%和64%，凸显了本框架带来的显著性能提升。我们进一步在CIFAR-10和CIFAR-100数据集上验证了框架的可扩展性，在MNIST和CIFAR-10上分别实现了最高30%和5%的相对宏观F1分数提升，同时将校准误差降低25%。复杂度分析证实了该方法的实时可行性，其延迟低于1毫秒且参数量小于0.02M。通过剪枝与可视化技术阐明决策路径，进一步增强了模型透明度。这些研究成果为特征选择提供了一种可扩展、可解释的解决方案，适用于需要实时自适应决策且人工干预最少的应用场景。