{"paper_id":"2503.02496","title":"To Hedge or Not to Hedge: Optimal Strategies for Stochastic Trade Flow Management","authors":["Philippe Bergault","Olivier Guéant","Hamza Bodor"],"paper_date":"2025-03-04","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2503.02496v1","page_url":"https://thequant.space/flowcharts/to-hedge-or-not-to-hedge-optimal-strategies-for-stochastic/","scores":{"empirical_rigor":3,"math_complexity":9,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes using reinforcement learning as an alternative to classical PDE‑based methods for determining optimal trading policies in stochastic trade‑flow management, and derives almost‑closed‑form solutions for quadratic execution costs.","quote":"Within the Almgren-Chriss framework, we derive almost-closed-form solutions in the case of quadratic execution costs, while more general cases require numerical methods. In particular, we discuss the challenges posed by artificial boundary conditions when using classical grid-based numerical PDE techniques and propose reinforcement learning methods as an alternative.","summary":"This paper addresses the trade-off between internalisation and externalisation in the management of stochastic trade flows. We consider agents who must absorb flows and manage risk by deciding whether to warehouse it or hedge in the market, thereby incurring transaction costs and market impact.…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Trade flows follow Brownian dynamics.","type":"model","stated":"explicit","quote":"Assuming Brownian dynamics for the trade flows,2 and absolutely continuous trading strategies, the inven-tory process (qt)t∈[0,T ] evolves as: dqt = vtdt + νdBt, (1) where q0 ∈R and ν ∈R+ are given, (vt)t∈[0,T ] represents the trading velocity of the trader, and (Bt)t∈[0,T ] is a standard Brownian motion.","support":"full"},{"assumption":"The asset price is a Brownian motion impacted linearly by the trading velocity.","type":"model","stated":"explicit","quote":"The asset price process (St)t∈[0,T ] is modelled as a Brownian motion impacted by the trader’s strategy: dSt = kvtdt + σdWt, (2) where S0 ∈R is given, σ ∈R∗ + is the volatility parameter, k ∈R+ represents the permanent market impact parameter, and (Wt)t∈[0,T ] is a standard Brownian motion.","support":"full"},{"assumption":"Execution cost function L(v) is strictly convex and asymptotically super‑linear (e.g., L(v)=ψ²|v|+ηv^{1+ϕ}).","type":"execution","stated":"explicit","quote":"In this paper, we primarily focus on cases where L is a strictly convex and asymptotically super-linear function, such as L(v) = ψ 2 |v| + ηv1+ϕ, with ψ ∈R+, η ∈R∗ +, and ϕ ∈R∗ +.","support":"full"},{"assumption":"The trader is risk‑averse and maximises expected CARA utility or a risk‑adjusted expectation.","type":"other","stated":"explicit","quote":"More precisely, we consider a risk-averse trader whose objective is either to maximise the expected CARA utility or a risk-adjusted expectation (à la Cartea-Jaimungal; see [15]) of their profit at a terminal time T. We show that, in both cases, the problem with quadratic execution costs can be tackled almost explic-itly, as it reduces to solving a matrix Riccati differential equation.","support":"full"},{"assumption":"The Brownian motions driving trade flow and price have constant correlation ρ.","type":"model","stated":"explicit","quote":"We assume that, together, (Bt)t∈[0,T ] and (Wt)t∈[0,T ] form a two-dimensional Brownian motion with a quadratic covariation coefficient ρ ∈[−1, 1].","support":"full"},{"assumption":"Inventory and cash processes are absolutely continuous and start from given deterministic values.","type":"model","stated":"explicit","quote":"Assuming Brownian dynamics for the trade flows,2 and absolutely continuous trading strategies, the inven-tory process (qt)t∈[0,T ] evolves as: dqt = vtdt + νdBt, (1) where q0 ∈R and ν ∈R+ are given, (vt)t∈[0,T ] represents the trading velocity of the trader, and (Bt)t∈[0,T ] is a standard Brownian motion. The trader’s cash account (Xt)t∈[0,T ] evolves according to: dXt = −vtStdt −L(vt)dt, (3) where X0 ∈R is given,","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Synthetic market environment","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Unless specified otherwise, inventory is measured in lots of 5000 shares.4 Environment parameters: • Trading horizon: T = 1 day • Discrete time step: ∆t = 1 100 day • Initial lot price: S0 = 500, 000 $ · lot−1 • Arithmetic volatility: σ = 10,","support":"full"}],"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":"Execution costs are modelled as L(v)=ψ²|v|+ηv² (linear spread term ψ and quadratic penalty η).","quote":"In this paper, we primarily focus on cases where L is a strictly convex and asymptotically super-linear function, such as L(v) = ψ 2 |v| + ηv1+ϕ, with ψ ∈R+, η ∈R∗ +, and ϕ ∈R∗ +. Unless specified otherwise, inventory is measured in lots of 5000 shares.4 Environment parameters: • Trading horizon: T = 1 day • Discrete time step: ∆t = 1 100 day • Initial lot price: S0 = 500, 000 $ · lot−1 • Arithmetic volatility: σ =","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Execution costs are modelled as L(v)=ψ²|v|+ηv² (linear spread term ψ and quadratic penalty η).","card_quote":"In this paper, we primarily focus on cases where L is a strictly convex and asymptotically super-linear function, such as L(v) = ψ 2 |v| + ηv1+ϕ, with ψ ∈R+, η ∈R∗ +, and ϕ ∈R∗ +. Unless specified otherwise, inventory is measured in lots of 5000 shares.4 Environment parameters: • Trading horizon: T = 1 day • Discrete time step: ∆t = 1 100 day • Initial lot price: S0 = 500, 000 $ · lot−1 • Arithmetic volatility: σ =","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"The RL method converges to near‑optimal solutions, achieving performance almost similar to the PDE‑based solution.","kind":"performance","quote":"We proposed the use of an RL-based approach as an alternative to a more classical PDE-based approach in order to determine optimal trading policies. According to our results, our RL method converges to near-optimal solutions successfully, resulting in per-formance almost similar to the PDE-based solution, or exact solutions in contexts where they are known.","support":"full"},{"finding":"The PDE‑based solution slightly outperforms the RL policy on average.","kind":"performance","quote":"On average, the PDE-based solution achieves a slight but consistent outperformance compared to the RL-based policy.","support":"full"},{"finding":"For quadratic execution costs the problem admits an almost‑closed‑form solution via a matrix Riccati differential equation.","kind":"theoretical","quote":"More precisely, we consider a risk-averse trader whose objective is either to maximise the expected CARA utility or a risk-adjusted expectation (à la Cartea-Jaimungal; see [15]) of their profit at a terminal time T. We show that, in both cases, the problem with quadratic execution costs can be tackled almost explic-itly, as it reduces to solving a matrix Riccati differential equation. In Section 3, we show that","support":"full"},{"finding":"When execution costs are purely linear (η=0) the RL policy captures the optimal control structure with a no‑trading zone and increasing execution speed outside it.","kind":"performance","quote":"The reinforcement learning agent successfully captures the policy structure, with no execution within a given interval and an execution speed that increases with inventory outside of this interval. However, the frontier between internalisation and externalisation varies more over time and the RL agent does not bring the inventory back to the frontier in one step but adopts a less aggressive approach.","support":"full"},{"finding":"The density of total rewards from the PDE solution is nearly indistinguishable from the closed‑form solution.","kind":"statistical","quote":"The PDE-based solution produces a density curve that is very similar to the closed-form solution, making them nearly indistinguishable in the plot.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":31,"citations":{"cited_by_in_corpus":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":1,"unclassified":1},"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":"2026-11-14T19:51:53Z"},"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/"}