{"paper_id":"2312.14044","title":"CVA Hedging by Risk-Averse Stochastic-Horizon Reinforcement Learning","authors":["Roberto Daluiso","Marco Pinciroli","Michele Trapletti","Edoardo Vittori"],"paper_date":"2023-12-21","paper_type":"methodological","paper_url":"https://arxiv.org/pdf/2312.14044v1","page_url":"https://thequant.space/flowcharts/cva-hedging-by-risk-averse-stochastic-horizon-reinforcement/","scores":{"empirical_rigor":6,"math_complexity":7.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a risk‑averse reinforcement‑learning framework with stochastic horizons for CVA hedging, including a Trust‑Region Volatility Optimization generalization and an importance‑sampling scheme.","quote":"We leverage recent advances on risk‑averse Reinforcement Learning developed specifically for option hedging with an ad hoc practice‑aligned objective function aware of pathwise volatility, generalizing them to stochastic horizons.","summary":"This work studies the dynamic risk management of the risk-neutral value of the potential credit losses on a portfolio of derivatives. Sensitivities-based hedging of such liability is sub-optimal because of bid-ask costs, pricing models which cannot be completely realistic, and a discontinuity at…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Foreign currencies are always exchanged against the reference currency and never between themselves.","type":"execution","stated":"explicit","quote":"In the above modelling, we are supposing that foreign currencies are always exchanged against the reference currency and never between themselves."},{"assumption":"Interest rates are known time‑independent constants for all cash accounts.","type":"market","stated":"explicit","quote":"We also assume that interest rates are known time‑independent constants for all cash accounts."},{"assumption":"FX rate dynamics follow a Geometric Brownian Motion with constant drift µP,φ and volatility σP,φ.","type":"model","stated":"explicit","quote":"We simulate the FX rate via a Geometric Brownian Motion (GBM) dφt/φt = µP,φ dt + σP,φ dW P,φ t , with µP,φ the drift, σP,φ the volatility."},{"assumption":"Default intensity follows a Cox‑Ingersoll‑Ross (CIR) process with constant parameters.","type":"model","stated":"explicit","quote":"We simulate the default intensity via the Cox Ingersoll Ross (CIR) model"},{"assumption":"Real‑world correlation between FX and default intensity drivers is zero.","type":"statistical","stated":"explicit","quote":"Real‑world correlation of Brownian drivers ρP λφ 0%."},{"assumption":"CDS trading cost is captured by a constant parameter γλ.","type":"execution","stated":"explicit","quote":"CDS trading cost parameter γλ 1.66 × 10⁻³"}]},"datasets":{"status":"available","items":[{"name":"Synthetic FX and default intensity data","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"... We simulate the default intensity via the Cox Ingersoll Ross (CIR) model"}],"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":"Transaction costs are modeled as Tt(N)=∑h∈H ¯T h t, with bid‑ask spreads φc¯c,± and cost parameters γλ for CDS.","quote":"Finally, we can compute the total transaction costs as Tt(N) :=","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Transaction costs are modeled as Tt(N)=∑h∈H ¯T h t, with bid‑ask spreads φc¯c,± and cost parameters γλ for CDS.","card_quote":"Finally, we can compute the total transaction costs as Tt(N) :=","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Importance sampling reduces noise in training and improves the risk‑averse objective ηπ compared to naive sampling.","kind":"performance","quote":"The noise reduction effect of importance sampling in training is confirmed whichever the risk aversion ..."},{"finding":"Optimized agents consistently save on hedging costs by reducing hedge rebalances and exploiting differences between risk‑neutral and real‑world probabilities.","kind":"performance","quote":"The optimized agents are always able to save on costs by a wise reduction of hedge rebalances, but also cleverly exploit the expected returns arising from any difference between risk‑neutral and real‑world probabilities..."},{"finding":"Agents trained with the proposed method outperform benchmark delta‑hedge and jump‑hedge strategies across a range of risk‑aversion parameters.","kind":"performance","quote":"Even without importance sampling, we do get agents with an interesting risk‑cost profile when compared to the two benchmarks"}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":17,"citations":{"cited_by_in_corpus":1,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"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":"2026-11-14T18:17:31Z"},"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/"}