{"paper_id":"2310.04336","title":"Applying Reinforcement Learning to Option Pricing and Hedging","authors":["Zoran Stoiljkovic"],"paper_date":"2023-10-06","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2310.04336v1","page_url":"https://thequant.space/flowcharts/applying-reinforcement-learning-to-option-pricing-and-hedgin/","scores":{"empirical_rigor":4,"math_complexity":7.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes the Q‑Learning Black‑Scholes (QLBS) model for pricing and hedging European options in a model‑free, data‑driven way.","quote":"This thesis provides an overview of the recent advances in reinforcement learning in pricing and hedging financial instruments, with a primary focus on a detailed explanation of the Q-Learning Black Scholes approach, introduced by Halperin (2017).","summary":"This thesis provides an overview of the recent advances in reinforcement learning in pricing and hedging financial instruments, with a primary focus on a detailed explanation of the Q-Learning Black Scholes approach, introduced by Halperin (2017). This reinforcement learning approach bridges the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Constant volatility of the underlying asset is assumed.","type":"model","stated":"explicit","quote":"Since this paper compares the performances of QLBS and BSM, constant volatility of the underlying asset is assumed."},{"assumption":"The QLBS model is not risk‑neutral; stock dynamics are modeled under the real probability measure P.","type":"model","stated":"explicit","quote":"The QLBS model is not assumed to be risk neutral, and therefore, the dynamics of the stock price are modeled under the real probability measure P."}]},"datasets":{"status":"available","items":[{"name":"Simulated European put option data","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"The algorithm's performance under different state variables and scenarios for a European put option."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Proportional transaction cost c = 0.01 is incorporated via a cash‑flow approach.","quote":"Finally, this part discusses a possible effect of transaction costs on QLBS, which are incorporated after the model-based QLBS optimal actions are calculated","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Proportional transaction cost c = 0.01 is incorporated via a cash‑flow approach.","card_quote":"Finally, this part discusses a possible effect of transaction costs on QLBS, which are incorporated after the model-based QLBS optimal actions are calculated","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"The QLBS model accurately captures the impact of underlying volatility on option prices.","kind":"performance","quote":"The QLBS model accurately captures the impact of underlying volatility on option prices."},{"finding":"QLBS pricing closely aligns with BSM prices across weekly, bi‑weekly, monthly, and semi‑annual hedging frequencies.","kind":"pricing-calibration","quote":"The algorithm generates prices that closely align with those of the BSM model, regardless of whether the hedging frequency is weekly, bi‑weekly, monthly, or semi‑annually."},{"finding":"QLBS performs well across various strike prices, with larger deviations from BSM for deep in‑the‑money options when risk aversion increases.","kind":"performance","quote":"The results reveal that QLBS performs well across various strike prices, where QLBS pricing differs more from the BSM model for deep in‑the‑money options when the risk aversion increases."},{"finding":"Proportional transaction costs can be incorporated using a cash‑flow approach, affecting terminal wealth.","kind":"other","quote":"Finally, it is shown that proportional transaction costs can be considered using the cash flow approach."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":34,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"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":1,"extracted_at":"2026-11-14T18:21:05Z"},"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/"}