{"paper_id":"2401.08600","title":"Reinforcement Learning and Deep Stochastic Optimal Control for Final Quadratic Hedging","authors":["Bernhard Hientzsch"],"paper_date":"2023-11-20","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2401.08600v1","page_url":"https://thequant.space/flowcharts/reinforcement-learning-and-deep-stochastic-optimal-control-f/","scores":{"empirical_rigor":7,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes two data‑driven approaches, Reinforcement Learning (RL) and Deep Trajectory‑based Stochastic Optimal Control (DTSOC), for hedging a European call option under a quadratic P&L objective.","quote":"We consider two data driven approaches, Reinforcement Learning (RL) and Deep Trajectory-based Stochastic Optimal Control (DTSOC) for hedging a European call option without and with transaction cost according to a quadratic hedging P&L objective at maturity (\"variance-optimal hedging\" or \"final quadratic hedging\").","summary":"We consider two data driven approaches, Reinforcement Learning (RL) and Deep Trajectory-based Stochastic Optimal Control (DTSOC) for hedging a European call option without and with transaction cost according to a quadratic hedging P&L objective at maturity (“variance-optimal hedging” or “final…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The hedging instruments are traded liquidly and hedging does not impact their prices.","type":"market","stated":"explicit","quote":"We assume here that the hedging instruments are traded liquidly and that the hedged instrument is such that it can be hedged without impacting the prices of the hedging instruments."},{"assumption":"The stochastic volatility in the log‑normal SABR test case is treated as a latent, unobserved state.","type":"model","stated":"explicit","quote":"We treat it here as a latent state that is not provided as input to the agent/policy."},{"assumption":"Stock dynamics follow either Black‑Scholes with constant volatility or log‑normal SABR with stochastic volatility.","type":"model","stated":"explicit","quote":"We assume the Black‑Scholes or SABR model for the simulation environment where the stock dynamics is given by dSt = µSt dt + σtSt dWt"},{"assumption":"Zero interest rates are assumed for the analytical variance‑optimal hedge derivations.","type":"statistical","stated":"explicit","quote":"for the case of zero interest rates) and applies them to the log‑normal SABR and the Rough Bergomi model."},{"assumption":"P&L at maturity can be written as a sum of step‑wise contributions for RL optimization.","type":"other","stated":"explicit","quote":"To apply RL approaches to these problems, P&L at maturity is written as sum of step‑wise contributions and variants of RL algorithms are implemented and used that minimize expectation of second moments of such sums."}]},"datasets":{"status":"available","items":[{"name":"Synthetic Black‑Scholes trajectories","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"We assume the Black‑Scholes or SABR model for the simulation environment where the stock dynamics is given by dSt = µSt dt + σtSt dWt"},{"name":"Synthetic log‑normal SABR trajectories","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"We assume the Black‑Scholes or SABR model for the simulation environment where the stock dynamics is given by dSt = µSt dt + σtSt dWt"}],"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":null,"quote":null,"source":"front_matter","rule":"R1","candidates":{"front_matter":"yes","evidence_card":"unclear","evidence_card_quoted":false},"meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Without transaction costs in the Black‑Scholes model, both RL and DTSOC match the performance of the variance‑optimal Delta hedge.","kind":"performance","quote":"Without transaction costs and in the Black‑Scholes model, both approaches match the performance of the variance‑optimal Delta hedge."},{"finding":"Without transaction costs in the log‑normal SABR model, both approaches match the performance of the variance‑optimal Bartlett’s Delta hedge.","kind":"performance","quote":"In the log‑normal SABR model without transaction costs, they match the performance of the variance‑optimal Barlett’s Delta hedge."},{"finding":"For non‑zero and increasing transaction costs, both RL‑QH and deep‑QH outperform the variance‑optimal Delta hedge on average, with deep‑QH doing so more consistently in the Black‑Scholes case.","kind":"performance","quote":"For non‑zero and increasing transaction costs, both RL‑QH and deep‑QH outperform the variance optimal Delta hedging on average, with deep‑QH doing so more consistently than RL‑QH in the Black‑Scholes case."},{"finding":"Agents trained on Black‑Scholes but tested on SABR trajectories match Bartlett’s Delta hedge in average cost, but exhibit larger variance (deep‑QH) and dramatically larger variance (RL‑QH).","kind":"performance","quote":"On average, RL‑QH and deep‑QH still match the performance of Bartlett’s Delta hedge, however showing larger variance (for deep‑QH) and dramatically larger variance (RL‑QH)."},{"finding":"Deep‑QH and RL‑QH agents match the (approximate) variance‑optimal strategies in average cost, with RL‑QH showing a wider spread of extreme gains and losses.","kind":"performance","quote":"Deep‑QH and RL‑QH agents match the (approximate) variance optimal strategies in average cost with comparable (deep‑QH) or wider (RL‑QH) variance and range, with RL‑QH allowing a wider range of both extreme gains and losses."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":26,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[{"paper":{"paper_id":"2510.16938","title":"A Topological Approach to Parameterizing Deep Hedging Networks","paper_date":"2025-10-19","authors":["Alok Das","Kiseop Lee"],"empirical_rigor":6.5,"page_url":"https://thequant.space/flowcharts/a-topological-approach-to-parameterizing-deep-hedging-networks/"},"how":"uses_method_or_data","quote":null}],"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":"2026-11-14T18:19:30Z"},"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/"}