模块化金融强化学习中信用分配的等信息评估
Equal-information evaluation of credit assignment in modular financial reinforcement learning
AI总结：
本研究针对模块化金融强化学习中信用分配难以评估的问题，提出结合等信息重构控制等的评估框架，经实验识别出三类评估失败，贡献了可复用的信用分配评估方法论。
摘要：
模块化金融强化学习中的信用分配难以评估，因为归因信号可能在不增加决策相关信息或改善经济结果的情况下提升组件损失。我们提出一种结合等信息重构控制、固定效用比较和预先指定下游护栏的评估框架。该框架在归因引导的模块化交易架构中实例化，并在三项受控研究中测试，涵盖更新分配、监督目标表示和投资组合风险控制。我们发现，在公开接口下，基于残差的分配可被普通损失预算控制精确复现；直接缺口监督可提升组件预测，但无法保留解码结果；在固定效用下，组件式评论者监督会相对于标量监督恶化风险条件确定等价和最大回撤。这些结果确定了三种不同的评估失败：冗余归因信号、表示诱导的预测权衡，以及组件监督与下游风险结果的不一致。一个保留的历史工程案例进一步表明，模块级学习主张为何需要运行级溯源。本研究的贡献是一种可复用的方法论，用于评估在部分可观测、延迟反馈和经济风险约束下运行的专家系统中的信用分配。
英文摘要：
Credit assignment in modular financial reinforcement learning is difficult to evaluate because an attributed signal may improve a component loss without adding decision-relevant information or improving economic outcomes. We propose an evaluation framework combining equal-information reconstruction controls, fixed-utility comparisons and prespecified downstream guardrails. The framework is instantiated in an attribution-guided modular trading architecture and tested in three controlled studies covering update allocation, supervision-target representation and portfolio risk control. We find that residual-based allocation is exactly reproduced by an ordinary loss-budget control under the disclosed interface; direct shortfall supervision improves component prediction but fails decoded-outcome preservation; and component-wise critic supervision worsens risk-condition certainty equivalent and drawdown relative to scalar supervision under fixed utility. These results identify three distinct evaluation failures: redundant attribution signals, representation-induced prediction trade-offs, and misalignment between component supervision and downstream risk outcomes. A preserved historical engineering case further shows why module-level learning claims require run-level provenance. The contribution is a reusable methodology for evaluating credit assignment in expert systems operating under partial observability, delayed feedback and economic risk constraints.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
