Problem
Research questions and friction points this paper is trying to address.
Portfolio Optimization
High-Dimensional Market Features
Adaptive Adjustment
Titans-QFWP: A Regime-Aware Hybrid Quantum Fast Weight Programmer for Portfolio Optimization
🤖 AI Summary
提出Titans-QFWP，结合量子快速权重编程与记忆机制的混合强化学习架构，用于适应性投资组合优化，并通过增强A3C^2框架处理高维市场特征。
📝 Abstract
We propose Titans-QFWP, a hybrid reinforcement learning architecture integrating a Quantum Fast Weight Programmer with Titans-style memory (Persistence, Surprise, and Forgetting) for adaptive portfolio optimization. To address high-dimensional market features, we introduce an enhanced A3C^2 framework with Hungarian-aligned K-means clustering and scaled log-return rewards. Evaluated on 468 S&P 500 stocks under an Equal-Parameter-Count (EPC) benchmark with approximately 3,000 trainable parameters, Titans-QFWP achieves strong performance (median ARR 0.4260, Calmar 8.5504, IR 0.8427). Ablation results reveal that quantum gating fundamentally reshapes memory component roles, with Persistence supporting drawdown control, Surprise contributing to return generation, and Forgetting providing additional stabilization. By stabilizing these quantum representations, the model enables defensive allocation during market drawdowns while preserving upside potential.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Quantum Fast Weight Programmer
Hybrid Reinforcement Learning
Portfolio Optimization
A3C^2 Framework
Memory Components
🔎 Similar Papers
No similar papers found.
