用双线性卷积提升强化学习可解释性，实现因果层面的注意力分析。
Bilinear Convolution Decomposition for Causal RL Interpretability
- 将卷积层替换为双线性结构，支持权重分解以解析模型内部机制。
- 在ProcGen环境中性能与原模型相当，且可分离通道与空间特征。
- 提出因果验证方法，用于检验概念探测器对关键对象（如奶酪）的追踪能力。
现有强化学习可解释性方法多依赖高阶归因或探测技术，仅提供相关性线索和粗粒度因果控制。本文提出用双线性卷积替代传统非线性卷积层，构建一类可解析的模型。实验表明，该类模型在无模型强化学习任务中表现与原模型相当，在ProcGen环境中进行了对比测试。双线性结构具备解析特性，可通过奇异值分解对感兴趣向量进行分解，分离通道与空间维度，揭示低秩可解释结构。进一步提出一种因果验证方法，用于评估基于概念的探测器有效性，以迷宫求解智能体追踪奶酪对象为例，验证其追踪能力的因果性。
原文摘要 · Abstract (English)
Efforts to interpret reinforcement learning (RL) models often rely on high-level techniques such as attribution or probing, which provide only correlational insights and coarse causal control. This work proposes replacing nonlinearities in convolutional neural networks (ConvNets) with bilinear variants, to produce a class of models for which these limitations can be addressed. We show bilinear model variants perform comparably in model-free reinforcement learning settings, and give a side by side comparison on ProcGen environments. Bilinear layers' analytic structure enables weight-based decomposition. Previous work has shown bilinearity enables quantifying functional importance through eigendecomposition, to identify interpretable low rank structure. We show how to adapt the decomposition to convolution layers by applying singular value decomposition to vectors of interest, to separate the channel and spatial dimensions. Finally, we propose a methodology for causally validating concept-based probes, and illustrate its utility by studying a maze-solving agent's ability to track a cheese object.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。