Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach

Abstract Portfolio optimization is a widely studied topic in quantitative finance. Recent advances in portfolio optimization have shown promising capabilities of deep reinforcement learning algorithms to dynamically allocate funds across various potential assets to meet the objectives of prospective...

Full description

Saved in:
Bibliographic Details
Main Authors: Himanshu Choudhary, Arishi Orra, Kartik Sahoo, Manoj Thakur
Format: Article
Language:English
Published: Springer 2025-05-01
Series:International Journal of Computational Intelligence Systems
Subjects:
Online Access:https://doi.org/10.1007/s44196-025-00875-8
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849688004891770880
author Himanshu Choudhary
Arishi Orra
Kartik Sahoo
Manoj Thakur
author_facet Himanshu Choudhary
Arishi Orra
Kartik Sahoo
Manoj Thakur
author_sort Himanshu Choudhary
collection DOAJ
description Abstract Portfolio optimization is a widely studied topic in quantitative finance. Recent advances in portfolio optimization have shown promising capabilities of deep reinforcement learning algorithms to dynamically allocate funds across various potential assets to meet the objectives of prospective investors. The reward function plays a crucial role in providing feedback to the agent and shaping its behavior to attain the desired goals. However, choosing an optimal reward function poses a significant challenge for risk-averse investors aiming to maximize returns while minimizing risk or pursuing multiple investment objectives. In this study, we attempt to develop a risk-adjusted deep reinforcement learning (RA-DRL) approach leveraging three DRL agents trained using distinct reward functions, namely, log returns, differential Sharpe ratio, and maximum drawdown to develop a unified policy that incorporates the essence of these individual agents. The actions generated by these agents are then fused by employing a convolutional neural network to provide a single risk-adjusted action. Instead of relying solely on a singular reward function, our approach integrates three different functions aiming at diverse objectives. The proposed approach is tested on daily data of four real-world stock market instances: Sensex, Dow, TWSE, and IBEX. The experimental results demonstrate the superiority of our proposed approach based on several risk and return performance metrics when compared with base DRL agents and benchmark methods.
format Article
id doaj-art-2ef6ea89a7794c6dbee30264a86149db
institution DOAJ
issn 1875-6883
language English
publishDate 2025-05-01
publisher Springer
record_format Article
series International Journal of Computational Intelligence Systems
spelling doaj-art-2ef6ea89a7794c6dbee30264a86149db2025-08-20T03:22:11ZengSpringerInternational Journal of Computational Intelligence Systems1875-68832025-05-0118111910.1007/s44196-025-00875-8Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward ApproachHimanshu Choudhary0Arishi Orra1Kartik Sahoo2Manoj Thakur3School of Mathematical and Statistical Sciences, Indian Institute of Technology MandiSchool of Mathematical and Statistical Sciences, Indian Institute of Technology MandiSchool of Mathematical and Statistical Sciences, Indian Institute of Technology MandiSchool of Mathematical and Statistical Sciences, Indian Institute of Technology MandiAbstract Portfolio optimization is a widely studied topic in quantitative finance. Recent advances in portfolio optimization have shown promising capabilities of deep reinforcement learning algorithms to dynamically allocate funds across various potential assets to meet the objectives of prospective investors. The reward function plays a crucial role in providing feedback to the agent and shaping its behavior to attain the desired goals. However, choosing an optimal reward function poses a significant challenge for risk-averse investors aiming to maximize returns while minimizing risk or pursuing multiple investment objectives. In this study, we attempt to develop a risk-adjusted deep reinforcement learning (RA-DRL) approach leveraging three DRL agents trained using distinct reward functions, namely, log returns, differential Sharpe ratio, and maximum drawdown to develop a unified policy that incorporates the essence of these individual agents. The actions generated by these agents are then fused by employing a convolutional neural network to provide a single risk-adjusted action. Instead of relying solely on a singular reward function, our approach integrates three different functions aiming at diverse objectives. The proposed approach is tested on daily data of four real-world stock market instances: Sensex, Dow, TWSE, and IBEX. The experimental results demonstrate the superiority of our proposed approach based on several risk and return performance metrics when compared with base DRL agents and benchmark methods.https://doi.org/10.1007/s44196-025-00875-8Deep reinforcement learningPortfolio optimizationConvolutional neural networkProximal policy optimizationQuantitative finance
spellingShingle Himanshu Choudhary
Arishi Orra
Kartik Sahoo
Manoj Thakur
Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach
International Journal of Computational Intelligence Systems
Deep reinforcement learning
Portfolio optimization
Convolutional neural network
Proximal policy optimization
Quantitative finance
title Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach
title_full Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach
title_fullStr Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach
title_full_unstemmed Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach
title_short Risk-Adjusted Deep Reinforcement Learning for Portfolio Optimization: A Multi-reward Approach
title_sort risk adjusted deep reinforcement learning for portfolio optimization a multi reward approach
topic Deep reinforcement learning
Portfolio optimization
Convolutional neural network
Proximal policy optimization
Quantitative finance
url https://doi.org/10.1007/s44196-025-00875-8
work_keys_str_mv AT himanshuchoudhary riskadjusteddeepreinforcementlearningforportfoliooptimizationamultirewardapproach
AT arishiorra riskadjusteddeepreinforcementlearningforportfoliooptimizationamultirewardapproach
AT kartiksahoo riskadjusteddeepreinforcementlearningforportfoliooptimizationamultirewardapproach
AT manojthakur riskadjusteddeepreinforcementlearningforportfoliooptimizationamultirewardapproach