{"paper_id":"2311.10801","title":"Reinforcement Learning with Maskable Stock Representation for Portfolio Management in Customizable Stock Pools","authors":["Wentao Zhang","Yilei Zhao","Shuo Sun","Jie Ying","Yonggang Xie","Zitao Song","Xinrun Wang","Bo An"],"paper_date":"2023-11-17","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2311.10801v4","page_url":"https://thequant.space/flowcharts/reinforcement-learning-with-maskable-stock-representation-fo/","scores":{"empirical_rigor":8,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes EarnMore, a reinforcement learning framework with maskable stock representation for portfolio management over customizable stock pools.","quote":"To tackle this challenge, we propose EarnMore, a rEinforcement leARNing framework with Maskable stOck REpresentation to handle PM with CSPs through one-shot training in a global stock pool (GSP).","summary":"Portfolio management (PM) is a fundamental financial trading task, which explores the optimal periodical reallocation of capitals into different stocks to pursue long-term profits. Reinforcement learning (RL) has recently shown its potential to train profitable agents for PM through interacting…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Customizable stock pools can be simulated by randomly masking stocks during training.","type":"model","stated":"implied","quote":"During training, we utilize the adaptive masking strategy developed by MAGE"},{"assumption":"The maskable stock representation can replace raw market data as input to the actor‑critic networks.","type":"model","stated":"implied","quote":"defined in Equation 4 instead of raw market data as input states for Actor and Critic."},{"assumption":"Daily price and technical indicator data from Yahoo Finance are sufficient for evaluating the RL framework.","type":"data","stated":"implied","quote":"In our experiment, we study daily data for 10,273 US stocks from Yahoo Finance, deriving indicators to understand market trends."}]},"datasets":{"status":"available","items":[{"name":"Yahoo Finance daily US stock data","provider":"Yahoo Finance","kind":"market-prices","access":"public","period":"2007-09-26 to 2022-06-26","universe":"10,273 US stocks (filtered to 3,094 stocks with 95 technical indicators)","quote":"In our experiment, we study daily data for 10,273 US stocks from Yahoo Finance, deriving indicators to understand market trends.","known_id":"yahoo-finance"},{"name":"SP500 subset","provider":null,"kind":"benchmark","access":"public","period":"2007-09-26 to 2022-06-26","universe":"420 stocks","quote":"Global stock pool (GSP) is the full set of stock pools containing 420 and 28 stocks respectively."},{"name":"DJ30 subset","provider":null,"kind":"benchmark","access":"public","period":"2007-09-26 to 2022-06-26","universe":"28 stocks","quote":"Global stock pool (GSP) is the full set of stock pools containing 420 and 28 stocks respectively."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"none_found","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0b","candidates":{"front_matter":"unclear","evidence_card":"no","evidence_card_quoted":false},"meaning":"no cost treatment was found in the passages the extractor read; that is not evidence that costs are not modeled"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"EarnMore significantly outperforms 14 baselines on 6 financial metrics, achieving over 40% improvement on profit.","kind":"performance","quote":"we demonstrate that EarnMore significantly outperforms 14 state-of-the-art baselines in terms of 6 popular financial metrics with over 40% improvement on profit."},{"finding":"On the SP500 global stock pool, EarnMore achieves a profit of 110.15% and ARR of 7.0%, far exceeding other methods.","kind":"performance","quote":"EarnMore 110.1507.0 2.28223.7 25.8 -19.7 43.4 95.1"},{"finding":"Ablation shows that removing maskable representation or re‑weighting reduces profit and increases risk metrics.","kind":"performance","quote":"Comparing EarnMore-w/o-M with EarnMore reveals a significant improvement due to the generalized pool-level maskable stock representation."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":11,"citations":{"cited_by_in_corpus":5,"by_independent_authors":5,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":2,"unclassified":3},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/DVampire/EarnMore","note":null},"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":"2026-11-14T18:19:28Z"},"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/"}