{"paper_id":"2511.15262","title":"Reinforcement Learning in Queue-Reactive Models: Application to Optimal Execution","authors":["Tomas Espana","Yadh Hafsi","Fabrizio Lillo","Edoardo Vittori"],"paper_date":"2025-11-19","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2511.15262v1","page_url":"https://thequant.space/flowcharts/reinforcement-learning-in-queue-reactive-models-application/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a reinforcement‑learning framework using a Double Deep Q‑Network to solve the optimal execution problem within a Queue‑Reactive Model of the limit order book.","quote":"In this work, we proposed a reinforcement‑learning framework for optimal execution within the Queue‑Reactive Model (QRM).","summary":"We investigate the use of Reinforcement Learning for the optimal execution of meta-orders, where the objective is to execute incrementally large orders while minimizing implementation shortfall and market impact over an extended period of time. Departing from traditional parametric approaches to…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"All order‑book queues are assumed non‑empty for simplicity.","type":"model","stated":"explicit","quote":"For simplicity, all queues q±i are considered non‑empty, as this represents the typical configuration of the invariant distribution π."},{"assumption":"The pre‑trade mid‑price equals the mid‑price just before the trade (pref(t‑k)=pmid(t‑k)).","type":"model","stated":"explicit","quote":"Furthermore, we assume pref(t−k)=pmid(t−k), with the surrounding volumes q±i sampled from the invariant distribution"},{"assumption":"The execution price is always the best ask.","type":"execution","stated":"explicit","quote":"Pτk the execution price, which in our setting is always the best ask."},{"assumption":"A linear terminal penalty proportional to remaining shares is applied to enforce full execution.","type":"execution","stated":"explicit","quote":"This penalty is equal to the number of shares remaining to be executed, scaled by a final penalty parameter α"},{"assumption":"The underlying Queue‑Reactive process is ergodic under mild conditions.","type":"model","stated":"explicit","quote":"with the surrounding volumes q±i sampled from the invariant distribution, consistent with the ergodicity of the process X under mild conditions."}]},"datasets":{"status":"available","items":[{"name":"Queue‑Reactive Model simulations","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"we employ the Queue‑Reactive Model to generate realistic and tractable limit order book simulations that encompass transient price impact, and nonlinear and dynamic order flow responses"}],"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":"Implementation shortfall (IS) is used as the cost metric; the reward is defined as the negative of IS.","quote":"Since the reward function is defined as the negative of the IS, minimizing IS is equivalent to maximizing the reward.","source":"front_matter","rule":"R3","candidates":{"front_matter":"yes","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Implementation shortfall (IS) is used as the cost metric; the reward is defined as the negative of IS.","card_quote":"Since the reward function is defined as the negative of the IS, minimizing IS is equivalent to maximizing the reward.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"execution-cost","findings":[{"finding":"The learned policy consistently outperforms the best benchmark across different market regimes, achieving up to 27% higher performance.","kind":"performance","quote":"it consistently exceeds the best benchmark, achieving up to 27% higher performance."},{"finding":"Feature‑gradient analysis shows that ask price and inventory are the primary determinants of action selection, while time has a small influence.","kind":"other","quote":"The results indicate that the ask price and inventory are the primary determinants of action selection, suggesting that the agent mainly reacts to immediate market conditions."},{"finding":"Q‑values decline over time for a fixed inventory, reflecting increasing risk of incomplete execution as the horizon shortens.","kind":"other","quote":"All plots reveal that, for a fixed inventory, Q‑values decline over time as the remaining horizon shortens, reflecting the agent’s increasing risk of incomplete execution"},{"finding":"The agent learns a policy that is both strategic and tactical, adapting effectively to order‑book conditions and outperforming standard approaches across multiple training configurations.","kind":"performance","quote":"Numerical simulation results show that the agent learns a policy that is both strategic and tactical, adapting effectively to order book conditions and outperforming standard approaches across multiple training configurations."}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":36,"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":"2026-11-14T17:21:27Z"},"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/"}