IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2509.14385.html

Adaptive and Regime-Aware RL for Portfolio Optimization

Author

Listed:
  • Gabriel Nixon Raj

Abstract

This study proposes a regime-aware reinforcement learning framework for long-horizon portfolio optimization. Moving beyond traditional feedforward and GARCH-based models, we design realistic environments where agents dynamically reallocate capital in response to latent macroeconomic regime shifts. Agents receive hybrid observations and are trained using constrained reward functions that incorporate volatility penalties, capital resets, and tail-risk shocks. We benchmark multiple architectures, including PPO, LSTM-based PPO, and Transformer PPO, against classical baselines such as equal-weight and Sharpe-optimized portfolios. Our agents demonstrate robust performance under financial stress. While Transformer PPO achieves the highest risk-adjusted returns, LSTM variants offer a favorable trade-off between interpretability and training cost. The framework promotes regime-adaptive, explainable reinforcement learning for dynamic asset allocation.

Suggested Citation

  • Gabriel Nixon Raj, 2025. "Adaptive and Regime-Aware RL for Portfolio Optimization," Papers 2509.14385, arXiv.org.
    • Handle: RePEc:arx:papers:2509.14385
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2509.14385
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Andrew Ang & Allan Timmermann, 2012. "Regime Changes and Financial Markets," Annual Review of Financial Economics, Annual Reviews, vol. 4(1), pages 313-337, October.
    2. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," Review of Finance, European Finance Association, vol. 33(5), pages 2223-2273.
    3. Kolm, Petter N. & Tütüncü, Reha & Fabozzi, Frank J., 2014. "60 Years of portfolio optimization: Practical challenges and current trends," European Journal of Operational Research, Elsevier, vol. 234(2), pages 356-371.
    4. Zhengyao Jiang & Dixing Xu & Jinjun Liang, 2017. "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem," Papers 1706.10059, arXiv.org, revised Jul 2017.
    5. Shihao Gu & Bryan Kelly & Dacheng Xiu, 2020. "Empirical Asset Pricing via Machine Learning," The Review of Financial Studies, Society for Financial Studies, vol. 33(5), pages 2223-2273.
    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. 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).
    2. Francisco Salas-Molina & David Pla-Santamaria & Ana Garcia-Bernabeu & Adolfo Hilario-Caballero, 2025. "An Empirical Evaluation of Distance Metrics in Hierarchical Risk Parity Methods for Asset Allocation," Computational Economics, Springer;Society for Computational Economics, vol. 66(6), pages 5189-5206, December.
    3. Maher Hamid, 2026. "Implementing domain-specific LLMs for strategic investment decisions: a retrospective case study comparing AI and human expertise," Digital Finance, Springer, vol. 8(1), pages 1-134, March.
    4. Muhammad Abro & Hassan Jaleel, 2026. "Regret-Driven Portfolios: LLM-Guided Smart Clustering for Optimal Allocation," Papers 2601.17021, arXiv.org.
    5. Varun Narayan Kannan Pillai & Akshay Ajith & Sumesh K J, 2026. "Generating Alpha: A Hybrid AI-Driven Trading System Integrating Technical Analysis, Machine Learning and Financial Sentiment for Regime-Adaptive Equity Strategies," Papers 2601.19504, arXiv.org.
    6. Arasteh, Abdollah, 2025. "A data-driven prediction method for multi-period portfolio optimization using the real options approach," Finance Research Letters, Elsevier, vol. 80(C).
    7. Shuo Sun & Rundong Wang & Bo An, 2021. "Reinforcement Learning for Quantitative Trading," Papers 2109.13851, arXiv.org.
    8. Gagan Deep & Akash Deep & William Lamptey, 2025. "Interpretable Hypothesis-Driven Trading:A Rigorous Walk-Forward Validation Framework for Market Microstructure Signals," Papers 2512.12924, arXiv.org.
    9. Dichtl, Hubert & Drobetz, Wolfgang & Otto, Tizian, 2023. "Forecasting Stock Market Crashes via Machine Learning," Journal of Financial Stability, Elsevier, vol. 65(C).
    10. Ngo, Vu Minh & Nguyen, Huan Huu & Van Nguyen, Phuc, 2023. "Does reinforcement learning outperform deep learning and traditional portfolio optimization models in frontier and developed financial markets?," Research in International Business and Finance, Elsevier, vol. 65(C).
    11. Caldeira, João F. & Santos, André A.P. & Torrent, Hudson S., 2023. "Semiparametric portfolios: Improving portfolio performance by exploiting non-linearities in firm characteristics," Economic Modelling, Elsevier, vol. 122(C).
    12. Conlon, Thomas & Cotter, John & Kynigakis, Iason, 2025. "Asset allocation with factor-based covariance matrices," European Journal of Operational Research, Elsevier, vol. 325(1), pages 189-203.
    13. Mustafa, Andy Ali & Lin, Ching-Yang & Kakinaka, Makoto, 2022. "Detecting market pattern changes: A machine learning approach," Finance Research Letters, Elsevier, vol. 47(PA).
    14. Yun-Shi Dai & Peng-Fei Dai & St'ephane Goutte & Duc Khuong Nguyen & Wei-Xing Zhou, 2025. "Moment connectedness and driving factors in the energy-food nexus: A time-frequency perspective," Papers 2510.24174, arXiv.org.
    15. Cirulli, Antonello & Walker, Patrick S., 2025. "Outperforming equal weighting," Economics Letters, Elsevier, vol. 255(C).
    16. Fabrizio Ghezzi & Anindo Sarkar & Thomas Quistgaard Pedersen & Allan Timmermann, 2025. "Optimal asset allocation and nonlinear return predictability from the dividend-price ratio," Annals of Operations Research, Springer, vol. 346(1), pages 415-445, March.
    17. Junyi Ye & Bhaskar Goswami & Jingyi Gu & Ajim Uddin & Guiling Wang, 2024. "From Factor Models to Deep Learning: Machine Learning in Reshaping Empirical Asset Pricing," Papers 2403.06779, arXiv.org.
    18. Andreas Koukorinis & Gareth W. Peters & Guido Germano, 2025. "Generative-Discriminative Machine Learning Models for High-Frequency Financial Regime Classification," Methodology and Computing in Applied Probability, Springer, vol. 27(2), pages 1-32, June.
    19. Uta Pigorsch & Sebastian Schafer, 2021. "High-Dimensional Stock Portfolio Trading with Deep Reinforcement Learning," Papers 2112.04755, arXiv.org.
    20. Michalski, Lachlan & Low, Rand Kwong Yew, 2024. "Determinants of corporate credit ratings: Does ESG matter?," International Review of Financial Analysis, Elsevier, vol. 94(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:2509.14385. 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.