{"paper_id":"2411.12746","title":"A Review of Reinforcement Learning in Financial Applications","authors":["Yahui Bai","Yuhe Gao","Runzhe Wan","Sheng Zhang","Rui Song"],"paper_date":"2024-11-01","paper_type":"survey-review","paper_url":"https://arxiv.org/pdf/2411.12746v1","page_url":"https://thequant.space/flowcharts/a-review-of-reinforcement-learning-in-financial-applications/","scores":{"empirical_rigor":3,"math_complexity":7,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes future research directions such as benchmarking, contextual RL, multi‑agent RL, and model‑based RL to address challenges and further enhance RL implementation in finance.","quote":"Finally, we propose future research directions, such as benchmarking, contextual RL, multi-agent RL, and model-based RL to address these challenges and to further enhance the implementation of RL in finance.","summary":"In recent years, there has been a growing trend of applying Reinforcement Learning (RL) in financial applications. This approach has shown great potential to solve decision-making tasks in finance. In this survey, we present a comprehensive study of the applications of RL in finance and conduct a…","strategy":null},"assumptions":{"status":"none_found","items":[]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"The authors introduce the RL Premium metric, calculated as (SR_RL − SR_Baseline)/SR_Baseline, to benchmark model performance across studies.","kind":"theoretical","quote":"The RL Premium is calculated by subtracting the Sharpe ratio of the strongest non-RL baseline SRBaseline from the RL method’s Sharpe ratio SRRL, then normalizing this difference by SRBaseline.","support":"full"},{"finding":"In the example of Jiang et al. (2017), the RL premium is (0.087 − 0.012)/0.012 = 6.25, indicating a significant performance gain from the RL method.","kind":"performance","quote":"The RL premium in this case would be calculated as (0.087 −0.012)/0.012 = 6.25, indicating a significant performance gain from the use of the RL method.","support":"partial"},{"finding":"Regression analysis shows that adding more state features may slightly improve portfolio management performance, but the effect is not statistically significant.","kind":"statistical","quote":"While upward slope demonstrates that ad-ditional information may slightly improve portfolio management performance, the effect is not significant based on p-value.","support":"full"},{"finding":"No significant differences are detected between the two algorithms (PG and DQN) in terms of RL Premium.","kind":"performance","quote":"From Figure 2f, no significant differences are detected between the two algorithms.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"not_extracted","supports":[],"contradicts":[],"qualifies":[],"compared_with":0,"citations":{"cited_by_in_corpus":3,"by_independent_authors":3,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":3,"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":2,"extracted_at":"2026-11-14T19:54:11Z"},"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/"}