{"paper_id":"2402.00515","title":"Developing A Multi-Agent and Self-Adaptive Framework with Deep Reinforcement Learning for Dynamic Portfolio Risk Management","authors":["Zhenglong Li","Vincent Tam","Kwan L. Yeung"],"paper_date":"2024-02-01","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2402.00515v4","page_url":"https://thequant.space/flowcharts/developing-a-multi-agent-and-self-adaptive-framework-with-de/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a multi‑agent and self‑adaptive framework (MASA) that combines RL‑based, solver‑based, and market‑observer agents to balance portfolio returns and risks.","quote":"Accordingly, a multi-agent and self-adaptive framework namely the MASA is proposed in which a sophisticated multi-agent reinforcement learning (RL) approach is adopted through two cooperating and reactive agents to carefully and dynamically balance the trade-off between the overall portfolio returns and their potential","summary":"Deep or reinforcement learning (RL) approaches have been adapted as reactive agents to quickly learn and respond with new investment strategies for portfolio management under the highly turbulent financial market environments in recent years. In many cases, due to the very complex correlations…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The first five years of data are used for training and the subsequent two years for validation.","type":"data","stated":"explicit","quote":"the first five-year data is used to train the model, followed by the subsequent data set of two years to validate the trained model."},{"assumption":"All data sets contain both upward and downward price trends and diverse market conditions to avoid bias.","type":"market","stated":"explicit","quote":"all the involved data sets contain both upward and downward trends of stock prices, and also various patterns of fluctuation for different market conditions so as to avoid any possible bias toward a specific approach under the evaluation."},{"assumption":"Portfolio risk is measured by the sampled variance (volatility) of daily returns over the trading period.","type":"statistical","stated":"explicit","quote":"The long-term portfolio risk 𝑉𝑜𝑙𝑝 is defined as the strategy volatility that is the sampled variance of the daily return rates 𝑟𝑝,𝑡 of a trading strategy over the whole trading period."},{"assumption":"Performance is evaluated using Sharpe Ratio, defined as (annualized return – risk‑free rate) divided by portfolio volatility.","type":"statistical","stated":"explicit","quote":"The Sharpe Ratio (SR) is a performance indicator for evaluating a portfolio in terms of the total annualized returns 𝑅𝑝, risk‑free rate 𝑟𝑓 and annualized long-term portfolio risk 𝑉𝑜𝑙𝑝."}]},"datasets":{"status":"available","items":[{"name":"CSI 300","provider":null,"kind":"market-prices","access":"unknown","period":"September 2013 to August 2023","universe":"top 10 stocks of the CSI 300 index","quote":"three challenging yet representative data sets of CSI 300, Dow Jones Industrial Average (DJIA) and S&P 500 indexes from September 2013 to August 2023"},{"name":"Dow Jones Industrial Average (DJIA)","provider":null,"kind":"market-prices","access":"unknown","period":"September 2013 to August 2023","universe":"top 10 stocks of the DJIA index","quote":"three challenging yet representative data sets of CSI 300, Dow Jones Industrial Average (DJIA) and S&P 500 indexes from September 2013 to August 2023"},{"name":"S&P 500","provider":null,"kind":"market-prices","access":"unknown","period":"September 2013 to August 2023","universe":"top 10 stocks of the S&P 500 index","quote":"three challenging yet representative data sets of CSI 300, Dow Jones Industrial Average (DJIA) and S&P 500 indexes from September 2013 to August 2023"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"no","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"MASA without market observer reduces risk (MDD 0.0119) and achieves a higher Sharpe Ratio compared with the single‑agent baseline.","kind":"performance","quote":"The resulting risks and MDD are dropped to 0.0119 and 31.7% respectively, with some further improvement on both the total returns and SR."},{"finding":"Adding the market observer agent further improves total annual returns and Sharpe Ratio over the dual‑agent MASA‑w/oMktObs.","kind":"performance","quote":"MASA can better estimate the potential risks while pursuing higher returns after considering more latest market information from the market observer agent."},{"finding":"The MASA framework outperforms ten representative RL‑based and algorithmic methods on the CSI 300, DJIA and S&P 500 data sets over the past 10 years.","kind":"performance","quote":"The obtained empirical results clearly reveal the remarkable performance of our proposed MASA framework based on the multi-agent RL approach when compared against those of other well-known RL-based approaches on the 3 data sets of widely recognised financial indexes"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"citations":{"cited_by_in_corpus":3,"by_independent_authors":2,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":2},"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":"2026-11-14T18:15:31Z"},"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/"}