- 學位論文
應用深度強化學習演算法於資產配置優化之比較
Comparison of Deep Reinforcement Learning Algorithms For Optimizing Portfolio Management
摘要
本文主要有三個命題，命題一，深度強化學習模型應用於資產配置是否需財務時間序列與統計的背景知識?命題二，比較不同的深度強化學習演算法在不同市場情境下之優劣。命題三，比較深度強化學習演算法與現代投資組合理論之績效表現，深度強化學習演算法是否具有實務應用價值?以三命題剖析應用深度強化學習演算法於資產配置之各類比較，命題一研究成果顯示，使用特徵資料如符合深度強化學習模型前提假設之馬可夫性，將使模型具事半功倍之成效；命題二研究成果顯示，不同深度強化學習模型具不同偏差與方差權衡之特性，可對應於實務資產管理權衡績效與模型穩定度之取捨；命題三研究成果顯示，深度強化學習模型顯著優於現代投資組合理論之均值方差模型，並輔以客戶體驗角度論述其價值性；三類比較以貫穿本文主旨，期能以客觀公允之方式交付具意涵的比較分析結果，俾提升深度強化學習模型應用於資產配置之有效性。
並列摘要
The purpose of this paper is three-fold. First, does the application of DRL require statistical (time-series) knowledge? The results revealed that using data that meets the model's assumptions will make the model more effective. Second, compare the pros and cons of DRL algorithms in different market. The results revealed that building DRL algorithms are forced to make decisions about the bias and variance. Ultimately, asset management companies have to find the correct balance for their customers. Third, What is the value of DRL? Compare the performance of DRL and MVO in detail to explain the value of DRL. The results revealed that DRL is significantly better than MVO, which can solve the pain points of current customers.
參考文獻
延伸閱讀
- 王衍晰（2020）。運用Soft Actor-Critic深度強化學習演算法優化投資配置組合〔碩士論文，國立政治大學〕。華藝線上圖書館。https://doi.org/10.6814/NCCU202001560
- 蔡慶源（2018）。對分散式深度學習的計算與傳輸之排程優化〔碩士論文，國立臺灣大學〕。華藝線上圖書館。https://doi.org/10.6342/NTU201801485
- Li, J. G. (2018). 應用深度學習於機器人理財之投資組合最佳化 [master's thesis, Tamkang University]. Airiti Library. https://www.airitilibrary.com/Article/Detail?DocID=U0002-2302201813271400
- Jeon, J. (2022). 人工特徵與深度學習特徵在基礎矩陣估算上之效能表現 [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU202202903
- Chen, S. A. (2018). Improving Deep Reinforcement Learning with Uncertainty-Based Interaction with Experts [master's thesis, National Taiwan University]. Airiti Library. https://doi.org/10.6342/NTU201803761