Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios

• URL: http://arxiv.org/abs/2510.07099v1
• Date: Wed, 08 Oct 2025 14:56:50 GMT
• Title: Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios
• Authors: Himanshu Choudhary, Arishi Orra, Manoj Thakur,
• Abstract summary: We propose an innovative framework, termed Diffusion-Augmented Reinforcement Learning (DARL), which integrates Denoising Diffusion Probabilistic Models (DDPMs) with Deep Reinforcement Learning (DRL) for portfolio management.<n>By leveraging DDPMs to generate synthetic market crash scenarios conditioned on varying stress intensities, our approach significantly enhances the robustness of training data.<n> Empirical evaluations demonstrate that DARL outperforms traditional baselines, delivering superior risk-adjusted returns and resilience against unforeseen crises.
• Score: 4.042562775811427
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In the ever-changing and intricate landscape of financial markets, portfolio optimisation remains a formidable challenge for investors and asset managers. Conventional methods often struggle to capture the complex dynamics of market behaviour and align with diverse investor preferences. To address this, we propose an innovative framework, termed Diffusion-Augmented Reinforcement Learning (DARL), which synergistically integrates Denoising Diffusion Probabilistic Models (DDPMs) with Deep Reinforcement Learning (DRL) for portfolio management. By leveraging DDPMs to generate synthetic market crash scenarios conditioned on varying stress intensities, our approach significantly enhances the robustness of training data. Empirical evaluations demonstrate that DARL outperforms traditional baselines, delivering superior risk-adjusted returns and resilience against unforeseen crises, such as the 2025 Tariff Crisis. This work offers a robust and practical methodology to bolster stress resilience in DRL-driven financial applications.

Related papers

• Generative Actor Critic [74.04971271003869]
  Generative Actor Critic (GAC) is a novel framework that decouples sequential decision-making by reframing textitpolicy evaluation as learning a generative model of the joint distribution over trajectories and returns.<n>Experiments on Gym-MuJoCo and Maze2D benchmarks demonstrate GAC's strong offline performance and significantly enhanced offline-to-online improvement compared to state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-12-25T06:31:11Z)
• Revisiting Entropy in Reinforcement Learning for Large Reasoning Models [54.96908589622163]
  We investigate the entropy dynamics of large language models trained withReinforcement learning with verifiable rewards (RLVR)<n>Our findings reveal that the number of off-policy updates, the diversity of training data, and the clipping thresholds in the optimization objective are critical factors influencing the entropy of LLMs trained with RLVR.
  arXiv  Detail & Related papers  (2025-11-08T12:50:41Z)
• Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets [57.179679246370114]
  In financial applications, reinforcement learning (RL) agents are commonly trained on historical data, where their actions do not influence prices.<n>During deployment, these agents trade in live markets where their own transactions can shift asset prices, a phenomenon known as market impact.<n>Traditional robust RL approaches address this model misspecification by optimizing the worst-case performance over a set of uncertainties.<n>We develop a novel class of elliptic uncertainty sets, enabling efficient and tractable robust policy evaluation.
  arXiv  Detail & Related papers  (2025-10-22T18:22:25Z)
• Adversarial Diffusion for Robust Reinforcement Learning [46.44328012099217]
  We introduce Adversarial Diffusion for Robust Reinforcement Learning (AD-RRL)<n>AD-RRL guides the diffusion process to generate worst-case trajectories during training, effectively optimizing the Conditional Value at Risk (CVaR) of the cumulative return.<n> Empirical results across standard benchmarks show that AD-RRL achieves superior robustness and performance compared to existing robust RL methods.
  arXiv  Detail & Related papers  (2025-09-28T12:34:35Z)
• Building crypto portfolios with agentic AI [46.348283638884425]
  The rapid growth of crypto markets has opened new opportunities for investors, but at the same time exposed them to high volatility.<n>This paper presents a practical application of a multi-agent system designed to autonomously construct and evaluate crypto-asset allocations.
  arXiv  Detail & Related papers  (2025-07-11T18:03:51Z)
• Your Offline Policy is Not Trustworthy: Bilevel Reinforcement Learning for Sequential Portfolio Optimization [82.03139922490796]
  Reinforcement learning (RL) has shown significant promise for sequential portfolio optimization tasks, such as stock trading, where the objective is to maximize cumulative returns while minimizing risks using historical data.<n>Traditional RL approaches often produce policies that merely memorize the optimal yet impractical buying and selling behaviors within the fixed dataset.<n>Our approach frames portfolio optimization as a new type of partial-offline RL problem and makes two technical contributions.
  arXiv  Detail & Related papers  (2025-05-19T06:37:25Z)
• Deep Reinforcement Learning for Investor-Specific Portfolio Optimization: A Volatility-Guided Asset Selection Approach [2.2835610890984164]
  This study proposes a volatility-guided portfolio optimization framework that dynamically constructs portfolios based on investors' risk profiles.<n>The efficacy of the proposed methodology is established using stocks from the Dow $30$ index.
  arXiv  Detail & Related papers  (2025-04-20T10:17:37Z)
• Reinforcement-Learning Portfolio Allocation with Dynamic Embedding of Market Information [12.032301674764552]
  We develop a portfolio allocation framework that leverages deep learning techniques to address challenges arising from high-dimensional, non-stationary, and low-signal-to-noise market information.<n>We design a reinforcement learning framework that integrates generative autoencoders and online meta-learning to dynamically embed market information.<n> Empirical analysis based on the top 500 U.S. stocks demonstrates that our framework outperforms common portfolio benchmarks.
  arXiv  Detail & Related papers  (2025-01-29T20:56:59Z)
• Explainable Post hoc Portfolio Management Financial Policy of a Deep Reinforcement Learning agent [44.99833362998488]
  We develop a novel Explainable Deep Reinforcement Learning (XDRL) approach for portfolio management. By executing our methodology, we can interpret in prediction time the actions of the agent to assess whether they follow the requisites of an investment policy.
  arXiv  Detail & Related papers  (2024-07-19T17:40:39Z)
• Deep Reinforcement Learning and Mean-Variance Strategies for Responsible Portfolio Optimization [49.396692286192206]
  We study the use of deep reinforcement learning for responsible portfolio optimization by incorporating ESG states and objectives. Our results show that deep reinforcement learning policies can provide competitive performance against mean-variance approaches for responsible portfolio allocation.
  arXiv  Detail & Related papers  (2024-03-25T12:04:03Z)
• Deep Hedging with Market Impact [0.20482269513546458]
  We propose a novel general market impact dynamic hedging model based on Deep Reinforcement Learning (DRL) The optimal policy obtained from the DRL model is analysed using several option hedging simulations and compared to commonly used procedures such as delta hedging.
  arXiv  Detail & Related papers  (2024-02-20T19:08:24Z)
• Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management [1.2016264781280588]
  A multi-agent reinforcement learning (RL) approach is proposed to balance the trade-off between the overall portfolio returns and their potential risks. The obtained empirical results clearly reveal the potential strengths of our proposed MASA framework.
  arXiv  Detail & Related papers  (2024-02-01T11:31:26Z)
• Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training [44.7991257631318]
  We propose a novel Split Variational Adrial Training (SVAT) method for risk-aware stock recommendation. By lowering the volatility of the stock recommendation model, SVAT effectively reduces investment risks and outperforms state-of-the-art baselines by more than 30% in terms of risk-adjusted profits.
  arXiv  Detail & Related papers  (2023-04-20T12:10:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.