{"paper_id":"2510.07099","title":"Diffusion-Augmented Reinforcement Learning for Robust Portfolio Optimization under Stress Scenarios","authors":["Himanshu Choudhary","Arishi Orra","Manoj Thakur"],"paper_date":"2025-10-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2510.07099v1","page_url":"https://thequant.space/flowcharts/diffusion-augmented-reinforcement-learning-for-robust-portfo/","scores":{"empirical_rigor":6.5,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes the Diffusion-Augmented Reinforcement Learning (DARL) framework that integrates Denoising Diffusion Probabilistic Models with Deep Reinforcement Learning for portfolio management.","quote":"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.","summary":"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…","strategy":"Diffusion-Augmented Reinforcement Learning (DARL)"},"assumptions":{"status":"available","items":[{"assumption":"Classical portfolio methods assume normally distributed returns and stationarity of data.","type":"statistical","stated":"implied","quote":"However, these classical methods rely on strong assumptions such as normally distributed returns and stationarity of data."},{"assumption":"Synthetic crash scenarios can be generated by conditioning DDPMs on stress intensity.","type":"model","stated":"explicit","quote":"By leveraging DDPMs to generate synthetic market crash scenarios conditioned on varying stress intensities"},{"assumption":"A transaction cost of 0.05% is applied to every trade.","type":"execution","stated":"explicit","quote":"a transaction cost of 0.05% is charged on every trade to mirror market frictions."},{"assumption":"The training data consists of daily closing prices for the Dow 30 stocks from 2011 to 2023.","type":"data","stated":"explicit","quote":"Daily closing prices for all DJI stocks were retrieved from Yahoo Finance, covering 1 January 2011 to 31 July 2025. For model development, the training window spans 1 January 2011 to 31 December 2023"}]},"datasets":{"status":"available","items":[{"name":"Dow Jones Industrial Average (DJI) 30 constituent stocks","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2011-01-01 to 2025-07-31","universe":"30 constituent stocks","quote":"We used data from the Dow Jones Industrial Average (DJI), comprising its 30 constituent stocks. Daily closing prices for all DJI stocks were retrieved from Yahoo Finance, covering 1 January 2011 to 31 July 2025.","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Daily closing prices for all DJI stocks were retrieved from Yahoo Finance, covering 1 January 2011 to 31 July 2025.","mentions":1,"used_in":1}],"sample":{"start":"2024-01","end":"2025-07","market":"Dow Jones Industrial Average stocks","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"0.05% per trade","quote":"a transaction cost of 0.05% is charged on every trade to mirror market frictions.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"0.05% per trade","card_quote":"a transaction cost of 0.05% is charged on every trade to mirror market frictions.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"DARL achieved the highest cumulative return of 59.52% and annualized return of 34.71%, outperforming the market index (17.88% cumulative, 11.07% annualized).","kind":"performance","quote":"It achieved the highest cumulative return (59.52%) and annualized return (34.71%), substantially surpassing the market index (17.88% cumulative, 11.07% annualized)."},{"finding":"DARL attained a Sharpe ratio of 1.91 and a Calmar ratio of 2.20, significantly higher than competing models.","kind":"performance","quote":"In terms of risk-adjusted performance, DARL demonstrated a Sharpe ratio of 1.91 and a Calmar ratio of 2.20, which are significantly higher than those of competing models."},{"finding":"The maximum drawdown of DARL was -15.76%, lower than Hybrid GA (-16.79%) and the Without Augmentation setup (-20.30%).","kind":"performance","quote":"the proposed model recorded a maximum drawdown of −15.76%, which is relatively lower than Hybrid GA (−16.79%) and Without Augmentation (−20.30%)"},{"finding":"During volatile market phases (Tariff Announcement), DARL showed faster recovery and more stable growth compared to traditional approaches.","kind":"performance","quote":"During volatile market phases (Tariff Announcement), the proposed displayed faster recovery and more stable growth, whereas traditional approaches like OLMAR, Hybrid GA, and the index suffered sharp declines and slower recoveries."}],"reported_performance":{"strategy":"Diffusion-Augmented Reinforcement Learning (DARL)","sharpe":1.9096,"sharpe_benchmark":0.7717,"annual_return_pct":34.7101,"total_return_pct":59.5253,"max_drawdown_pct":15.7598},"out_of_sample":{"method":"holdout","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":65,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:25:17Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}