IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2602.17098.html

Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization

Author

Listed:
  • Srijan Sood
  • Kassiani Papasotiriou
  • Marius Vaiciulis
  • Tucker Balch

Abstract

Portfolio Management is the process of overseeing a group of investments, referred to as a portfolio, with the objective of achieving predetermined investment goals. Portfolio optimization is a key component that involves allocating the portfolio assets so as to maximize returns while minimizing risk taken. It is typically carried out by financial professionals who use a combination of quantitative techniques and investment expertise to make decisions about the portfolio allocation. Recent applications of Deep Reinforcement Learning (DRL) have shown promising results when used to optimize portfolio allocation by training model-free agents on historical market data. Many of these methods compare their results against basic benchmarks or other state-of-the-art DRL agents but often fail to compare their performance against traditional methods used by financial professionals in practical settings. One of the most commonly used methods for this task is Mean-Variance Portfolio Optimization (MVO), which uses historical time series information to estimate expected asset returns and covariances, which are then used to optimize for an investment objective. Our work is a thorough comparison between model-free DRL and MVO for optimal portfolio allocation. We detail the specifics of how to make DRL for portfolio optimization work in practice, also noting the adjustments needed for MVO. Backtest results demonstrate strong performance of the DRL agent across many metrics, including Sharpe ratio, maximum drawdowns, and absolute returns.

Suggested Citation

  • Srijan Sood & Kassiani Papasotiriou & Marius Vaiciulis & Tucker Balch, 2026. "Deep Reinforcement Learning for Optimal Portfolio Allocation: A Comparative Study with Mean-Variance Optimization," Papers 2602.17098, arXiv.org.
    • Handle: RePEc:arx:papers:2602.17098
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2602.17098
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Francisco Caio Lima Paiva & Leonardo Kanashiro Felizardo & Reinaldo Augusto da Costa Bianchi & Anna Helena Reali Costa, 2021. "Intelligent Trading Systems: A Sentiment-Aware Reinforcement Learning Approach," Papers 2112.02095, arXiv.org.
    2. Alireza Ghahtarani & Ahmed Saif & Alireza Ghasemi, 2022. "Robust portfolio selection problems: a comprehensive review," Operational Research, Springer, vol. 22(4), pages 3203-3264, September.
    3. David W. Lu, 2017. "Agent Inspired Trading Using Recurrent Reinforcement Learning and LSTM Neural Networks," Papers 1707.07338, arXiv.org.
    4. David Silver & Julian Schrittwieser & Karen Simonyan & Ioannis Antonoglou & Aja Huang & Arthur Guez & Thomas Hubert & Lucas Baker & Matthew Lai & Adrian Bolton & Yutian Chen & Timothy Lillicrap & Fan , 2017. "Mastering the game of Go without human knowledge," Nature, Nature, vol. 550(7676), pages 354-359, October.
    5. R. Cont, 2001. "Empirical properties of asset returns: stylized facts and statistical issues," Quantitative Finance, Taylor & Francis Journals, vol. 1(2), pages 223-236.
    6. Zhipeng Liang & Hao Chen & Junhao Zhu & Kangkang Jiang & Yanran Li, 2018. "Adversarial Deep Reinforcement Learning in Portfolio Management," Papers 1808.09940, arXiv.org, revised Nov 2018.
    7. Jay Cao & Jacky Chen & John Hull & Zissis Poulos, 2021. "Deep Hedging of Derivatives Using Reinforcement Learning," Papers 2103.16409, arXiv.org.
    8. Li Chen & Simai He & Shuzhong Zhang, 2011. "When all risk-adjusted performance measures are the same: in praise of the Sharpe ratio," Quantitative Finance, Taylor & Francis Journals, vol. 11(10), pages 1439-1447.
    9. Alireza Ghahtarani & Ahmed Saif & Alireza Ghasemi, 2021. "Robust Portfolio Selection Problems: A Comprehensive Review," Papers 2103.13806, arXiv.org, revised Jan 2022.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Ben Hambly & Renyuan Xu & Huining Yang, 2021. "Recent Advances in Reinforcement Learning in Finance," Papers 2112.04553, arXiv.org, revised Feb 2023.
    2. Yannick Limmer & Blanka Horvath, 2023. "Robust Hedging GANs," Papers 2307.02310, arXiv.org.
    3. Ben Hambly & Renyuan Xu & Huining Yang, 2023. "Recent advances in reinforcement learning in finance," Mathematical Finance, Wiley Blackwell, vol. 33(3), pages 437-503, July.
    4. Svitlana Vyetrenko & David Byrd & Nick Petosa & Mahmoud Mahfouz & Danial Dervovic & Manuela Veloso & Tucker Hybinette Balch, 2019. "Get Real: Realism Metrics for Robust Limit Order Book Market Simulations," Papers 1912.04941, arXiv.org.
    5. Alexandre Carbonneau & Fr'ed'eric Godin, 2021. "Deep equal risk pricing of financial derivatives with non-translation invariant risk measures," Papers 2107.11340, arXiv.org.
    6. Qi, Yue & Liao, Kezhi & Liu, Tongyang & Zhang, Yu, 2022. "Originating multiple-objective portfolio selection by counter-COVID measures and analytically instigating robust optimization by mean-parameterized nondominated paths," Operations Research Perspectives, Elsevier, vol. 9(C).
    7. Mirza Sikalo & Almira Arnaut-Berilo & Adela Delalic, 2023. "A Combined AHP-PROMETHEE Approach for Portfolio Performance Comparison," IJFS, MDPI, vol. 11(1), pages 1-15, March.
    8. Pejman Peykani & Roya Soltani & Cristina Tanasescu & Seyed Ehsan Shojaie & Alireza Jandaghian, 2025. "The Robust Malmquist Productivity Index: A Framework for Measuring Productivity Changes over Time Under Uncertainty," Mathematics, MDPI, vol. 13(11), pages 1-27, May.
    9. Vrinda Dhingra & S. K. Gupta, 2025. "An Empirical Study of Robust Mean-Variance Portfolios with Short Selling," Computational Economics, Springer;Society for Computational Economics, vol. 66(3), pages 1943-1968, September.
    10. Sehgal, Ruchika & Sharma, Amita & Mansini, Renata, 2023. "Worst-case analysis of Omega-VaR ratio optimization model," Omega, Elsevier, vol. 114(C).
    11. Sekine, Eiko & Yamanaka, Kazuo, 2022. "A non-probabilistic approach to efficient portfolios," International Review of Financial Analysis, Elsevier, vol. 83(C).
    12. Nathan Lassance & Frédéric Vrins, 2021. "Minimum Rényi entropy portfolios," Annals of Operations Research, Springer, vol. 299(1), pages 23-46, April.
    13. Alejandra de la Rica Escudero & Eduardo C. Garrido-Merchan & Maria Coronado-Vaca, 2024. "Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent," Papers 2407.14486, arXiv.org.
    14. Zoran Stoiljkovic, 2023. "Applying Reinforcement Learning to Option Pricing and Hedging," Papers 2310.04336, arXiv.org.
    15. Kinyua, Johnson D. & Mutigwe, Charles & Cushing, Daniel J. & Poggi, Michael, 2021. "An analysis of the impact of President Trump’s tweets on the DJIA and S&P 500 using machine learning and sentiment analysis," Journal of Behavioral and Experimental Finance, Elsevier, vol. 29(C).
    16. Hongxin Zhao & Yilun Jiang & Yizhou Yang, 2023. "Robust and Sparse Portfolio: Optimization Models and Algorithms," Mathematics, MDPI, vol. 11(24), pages 1-20, December.
    17. Waga, Mateus & Valladão, Davi & Street, Alexandre, 2025. "Robust portfolio optimization meets Arbitrage Pricing Theory," European Journal of Operational Research, Elsevier, vol. 326(3), pages 558-568.
    18. Hsieh, Chung-Han, 2024. "On solving robust log-optimal portfolio: A supporting hyperplane approximation approach," European Journal of Operational Research, Elsevier, vol. 313(3), pages 1129-1139.
    19. Kang Gao & Stephen Weston & Perukrishnen Vytelingum & Namid R. Stillman & Wayne Luk & Ce Guo, 2023. "Deeper Hedging: A New Agent-based Model for Effective Deep Hedging," Papers 2310.18755, arXiv.org.
    20. Yu, Pengrui & Liu, Siya & Jin, Chengneng & Gu, Runsheng & Gong, Xiaomin, 2025. "Optimization-based spectral end-to-end deep reinforcement learning for equity portfolio management," Pacific-Basin Finance Journal, Elsevier, vol. 91(C).

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2602.17098. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.