[论文] Internalizing Investment Mandates: A Neurosymbolic RL Approach to Port...

论文概要

研究领域: ML 作者: Zeynep Yıldız, Satchit Chatterji, Ercan Atam, Erman Acar 发布时间: 2026-11-12 arXiv: 2611.17329

中文摘要

机构投资组合须遵循投资政策声明规定的资产配置约束，这些约束通常以市场状态信息为条件。深度强化学习虽能优化财务表现，但通常不保证规则合规，难以直接部署。现有神经符号方法如概率逻辑策略梯度（PLPG）通过可微符号监督实现满足约束的强化学习，但假设动作空间有限且离散。我们提出一种受 PLPG 启发的连续分配方法：用重参数化蒙特卡洛采样估计策略自身所执行动作满足投资授权的概率，并将其加入训练目标。推理时无需任何事后拦截机制，合规性由智能体在训练中内化。直接对确定性均值动作（不做任何修正）进行审计，该策略将一套六规则、随市场状态切换的授权违规率从非约束 RL 的 96-98%、奖励惩罚基线的 33.4% 降至 4.8%——表明连续动作神经符号策略能够实质性地内化符号约束。

原文摘要

Institutional portfolios operate under investment policy statements that specify asset allocation constraints, often conditioned on market regime information. Deep reinforcement learning has been shown to optimize financial performance but typically does not enforce rule compliance, making it unsuitable for real-world deployment. Existing neurosymbolic methods such as Probabilistic Logic Policy Gradient (PLPG) offer constraint-satisfying reinforcement learning (RL) via differentiable symbolic supervision but assume a finite, discrete action space. We present a PLPG-inspired continuous allocation method that estimates the probability that the policy's own executed action satisfies the investment mandate, using reparameterized Monte Carlo sampling, and adds it to the training objective. No p...

#论文 #arXiv #ML #小凯