{"paper_id":"2412.16175","title":"Mean--Variance Portfolio Selection by Continuous-Time Reinforcement Learning: Algorithms, Regret Analysis, and Empirical Study","authors":["Yilie Huang","Yanwei Jia","Xun Yu Zhou"],"paper_date":"2024-12-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2412.16175v2","page_url":"https://thequant.space/flowcharts/mean--variance-portfolio-selection-by-continuous-time-reinfo/","scores":{"empirical_rigor":7.5,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a data‑driven continuous‑time reinforcement‑learning approach for mean‑variance portfolio selection, including a specific algorithm for multi‑stock Black‑Scholes markets with a sublinear regret guarantee.","quote":"Based on the recently developed reinforcement learning (RL) theory for diffusion processes, we present a general data‑driven RL approach that learns the pre‑committed investment strategy directly without attempting to learn or estimate the market coefficients. For multi‑stock Black‑Scholes markets without factors, we f","summary":"We study continuous-time mean–variance portfolio selection in markets where stock prices are diffusion processes driven by observable factors that are also diffusion processes, yet the coefficients of these processes are unknown. Based on the recently developed reinforcement learning (RL) theory…","strategy":"CTRL"},"assumptions":{"status":"available","items":[{"assumption":"Stock prices and observable factors follow diffusion processes with unknown coefficients.","type":"market","stated":"explicit","quote":"stock prices are diffusion processes driven by observable factors that are also diffusion processes, yet the coefficients of these processes are unknown."},{"assumption":"In the algorithmic analysis, the market is a frictionless multi‑stock Black‑Scholes market without any factor F.","type":"model","stated":"explicit","quote":"we present an RL algorithm for a frictionless, multi‑stock Black–Scholes market without any factor F, i.e., the stock prices follow multi‑dimensional geometric Brownian motions."},{"assumption":"No portfolio constraints such as no‑shorting or leverage limits are imposed in the empirical comparison.","type":"execution","stated":"explicit","quote":"we compare all the methods without imposing additional portfolio constraints (such as no‑shorting or a leverage constraint)."},{"assumption":"Daily returns are computed from dividend‑adjusted closing prices.","type":"data","stated":"explicit","quote":"Daily returns are computed based on dividend‑adjusted closing prices."},{"assumption":"Transaction cost analysis assumes a flat 50 bps proportional cost per trade.","type":"other","stated":"explicit","quote":"recompute all the performance metrics assuming a 50 bps proportional transaction cost as in DeMiguel et al. (2009b)."},{"assumption":"The regret analysis is derived specifically for the Black‑Scholes environment and does not cover stochastic volatility or jumps.","type":"other","stated":"explicit","quote":"we are able to derive a sublinear regret only for the Black–Scholes environment, without considering more stylized facts of asset returns such as stochastic volatility and jumps."}]},"datasets":{"status":"available","items":[{"name":"Wharton Research Data Services and Yahoo Finance price data","provider":"Wharton Research Data Services; Yahoo Finance","kind":"market-prices","access":"commercial","period":"1990-01 to 2020-01","universe":"S&P 500 constituents, first 300 stocks alphabetically","quote":"The dataset used in this study is obtained from the Wharton Research Data Services and Yahoo Finance. Our asset universe consists of stocks that were constituents of the S&P 500 index and remained continuously listed with available daily trading data from January 1, 1990 to January 1, 2020. From this universe, we const","known_id":"wrds"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"5.1 Experimental setup Data and asset universe The dataset used in this study is obtained from the Wharton Research Data Services and Yahoo Finance.","mentions":1,"used_in":1}],"sample":{"start":"2000","end":"2020","market":"S&P 500 constituents","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":true,"detail":"A flat 50 bps proportional transaction cost is applied to all trades when reporting net‑of‑cost performance.","quote":"recompute all the performance metrics assuming a 50 bps proportional transaction cost as in DeMiguel et al. (2009b).","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"A flat 50 bps proportional transaction cost is applied to all trades when reporting net‑of‑cost performance.","card_quote":"recompute all the performance metrics assuming a 50 bps proportional transaction cost as in DeMiguel et al. (2009b).","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"CTRL achieves the highest average annualized return (12.211%) and Sharpe ratio (0.531) among all 14 methods over 2000‑2020.","kind":"performance","quote":"CTRL 12.211% (0.219%) 0.232 (0.003) 0.531 (0.010) 0.865 (0.017) 0.200 (0.005) 0.621 (0.009) 521 (30)"},{"finding":"Even after accounting for 50 bps transaction costs, CTRL still leads in return, Sharpe, Calmar ratios and has the shortest recovery time.","kind":"performance","quote":"CTRL still achieves the highest average annualized return , Sharpe ratio, Calmar ratio and the shortest recovery time."},{"finding":"CTRL exhibits the lowest monthly turnover and most modest position concentrations under transaction costs.","kind":"performance","quote":"CTRL continues to have the lowest monthly turnover rates and least concentrated positions. In particular, the maximum long and short positions under CTRL remain below 20% and 2%, respectively."},{"finding":"In the bear subperiod (2000‑2010), CTRL attains the highest return (9.788%) and Sharpe ratio (0.367), outperforming the next best method by a larger margin.","kind":"performance","quote":"CTRL achieves the highest annualized return (9.788%) and Sharpe ratio (0.367), as well as the best Sortino and Calmar ratios."},{"finding":"The proposed algorithm enjoys a provable sublinear regret bound in terms of the Sharpe ratio for the Black‑Scholes market.","kind":"theoretical","quote":"we further devise an algorithm and prove its performance guarantee by deriving a sublinear regret bound in terms of the Sharpe ratio."}],"reported_performance":{"strategy":"CTRL","sharpe":0.232,"sharpe_benchmark":0.311,"annual_return_pct":12.211,"total_return_pct":null,"max_drawdown_pct":62.1},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":32,"citations":{"cited_by_in_corpus":7,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":3,"unclassified":4},"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":"2026-11-14T17:50:48Z"},"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/"}