{"paper_id":"2312.11797","title":"Data-Driven Merton's Strategies via Policy Randomization","authors":["Min Dai","Yuchao Dong","Yanwei Jia","Xun Yu Zhou"],"paper_date":"2023-12-19","paper_type":"perspective-policy","paper_url":"https://arxiv.org/pdf/2312.11797v2","page_url":"https://thequant.space/flowcharts/data-driven-mertons-strategies-via-policy-randomization/","scores":{"empirical_rigor":6,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes an auxiliary problem using Gaussian policy randomization and develops online and offline actor‑critic reinforcement learning algorithms to solve Merton's investment problem in a data‑driven way.","quote":"We propose an auxiliary problem in which the agent can invoke policy randomization according to a specific class of Gaussian distributions, and prove that the mean of its optimal Gaussian policy solves the original Merton problem.","summary":"We study Merton’s expected utility maximization problem in an incomplete market, characterized by a factor process in addition to the stock price process, where all the model primitives are unknown. The agent under consideration is a price taker who has access only to the stock and factor value…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The market is incomplete and includes a factor process in addition to the stock price process.","type":"market","stated":"explicit","quote":"characterized by a factor process in addition to the stock price process"},{"assumption":"The agent only observes the stock price, factor value, and instantaneous volatility.","type":"data","stated":"explicit","quote":"has access only to the stock and factor value processes and the instantaneous volatility"},{"assumption":"The temperature (exploration) parameter λ is strictly positive, so the learned policy is always randomized.","type":"model","stated":"explicit","quote":"Finally, note that our method does not permit λ “ 0 and therefore always learns a randomized policy"},{"assumption":"A stochastic volatility model is used for the market dynamics.","type":"model","stated":"explicit","quote":"A stochastic volatility model is specified by µpt,xq …"},{"assumption":"Training data are generated synthetically with daily observations over 20 years.","type":"data","stated":"explicit","quote":"we generate a training dataset with daily data for 20 years, and each time we randomly sample a consecutive subsequence from that dataset with a length of 1 year as one episode for training"}]},"datasets":{"status":"available","items":[{"name":"Synthetic daily market data (20‑year horizon)","provider":null,"kind":"synthetic","access":"unknown","period":"20 years of daily data","universe":null,"quote":"we generate a training dataset with daily data for 20 years, and each time we randomly sample a consecutive subsequence from that dataset with a length of 1 year as one episode for training"}],"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":"Both RL methods outperform the plug‑in and ERM baselines on all metrics except annualized return, with RL‑NN achieving a Sharpe ratio of 0.306 versus 0.203 for the B‑H method.","kind":"performance","quote":"We observe the two RL methods outperform the other two methods in all the metrics except the annualized return (B-H has 5.9%, slightly higher than 5.6% by RL with neural networks). In particular, RL with neural networks beats the other methods by significant margins in most criteria including the Sharpe ratio."},{"finding":"RL strategies have markedly smaller maximum drawdowns and much shorter recovery times compared with the other methods.","kind":"performance","quote":"the two RL methods have remarkably smaller maximum drawdowns during the whole period"},{"finding":"RL algorithms perform better than ERM when the sample size is small (fewer than 100 episodes).","kind":"performance","quote":"Figure 1 shows that, with a small size dataset (i.e. fewer than 100 episodes), ERM performs poorly compared with our method using λ “ 0.01,0.1,1,10,100."},{"finding":"RL with neural networks consistently outperforms other methods during the volatile 2000‑2010 period, including the dot‑com bust and the 2007‑2008 financial crisis.","kind":"performance","quote":"It is clear that RL with neural networks outperforms (in terms of portfolio worth) all the others prior to around 2020"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":7,"by_independent_authors":6,"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":"2026-11-14T18:17:41Z"},"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/"}