{"paper_id":"2307.04754","title":"Action-State Dependent Dynamic Model Selection","authors":["Francesco Cordoni","Alessio Sancetta"],"paper_date":"2023-07-07","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2307.04754v2","page_url":"https://thequant.space/flowcharts/action-state-dependent-dynamic-model-selection/","scores":{"empirical_rigor":7,"math_complexity":8,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a reinforcement learning algorithm to dynamically select among portfolio models accounting for rebalancing costs.","quote":"A Reinforcement learning algorithm is used to approximate and estimate from the data the optimal solution to this dynamic programming problem.","summary":"A model among many may only be best under certain states of the world. Switching from a model to another can also be costly. Finding a procedure to dynamically choose a model in these circumstances requires to solve a complex estimation procedure and a dynamic programming problem. A Reinforcement…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"State‑action pairs are constructed with a bounded action set and exogenous state component.","type":"data","stated":"explicit","quote":"Assumption 1 (State Action Pair) The state action pair (St, At)t≥1 and A0 satisfy (5) where |A| is a bounded integer, St = (˜St, At−1) where ˜St takes values in some set ˜S, and (˜St)t≥1 is generated independently of (At)t≥0."},{"assumption":"The state process is a strictly stationary Markov chain with exponentially decaying beta‑mixing coefficients.","type":"statistical","stated":"explicit","quote":"Assumption 2 (Markov Assumption) The sequence of states S := (St)≥1 is a strictly stationary Markov process with beta mixing coefficients (βq)q≥1 satisfying βq ≲e−Cβq for some constant Cβ > 0."},{"assumption":"Rewards have finite moments of order at least two.","type":"statistical","stated":"explicit","quote":"Assumption 3 (Moments) We have that maxa∈A |R (T a·; θa (·))|v,P < ∞ for v ≥2."},{"assumption":"Reward‑parameter maps θa(s) are independent of the state sequence and measurable at time zero.","type":"model","stated":"explicit","quote":"→θa (s) is possibly random, but independent of the sequence of states (St)t≥1 and measurable at time t = 0."},{"assumption":"The approximating function class is a K‑dimensional linear span of basis functions.","type":"model","stated":"explicit","quote":"Assumption 5 (Approximating Function Class) The function space in (6) with functions {φl : l = 1, 2, ..., K} is a K dimensional vector space or a subset of it."}]},"datasets":{"status":"available","items":[{"name":"S&P 500 stock constituents","provider":"Kaggle","kind":"market-prices","access":"public","period":null,"universe":"S&P 500 constituents","quote":"The data for the stock constituents of the S&P500 were downloaded from Kaggle https://www.kaggle.com/datasets/andrewmvd/sp-500-stocks?resource=download&select=sp500_companies.csv.","known_id":"kaggle"}],"known":[{"id":"kaggle","name":"Kaggle","provider":"Kaggle","kind":"other","access":"public","quote":"S.2 Additional Details for Section 5 The data for the stock constituents of the S&P500 were downloaded from Kaggle https: //www.kaggle.com/datasets/andrewmvd/sp-500-stocks?resource=download&select= sp500_companies.csv.","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"available","modeled":"yes","headline_net_of_costs":null,"detail":"Costs are set equal to a constant times the relative turnover, where relative turnover is the ℓ1 norm of the change in portfolio weights.","quote":"Transaction costs can be set equal to a constant times the relative turnover. The relative turnover is the ℓ1 norm of wa −wa′.","source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"yes","evidence_card_quoted":true},"card_detail":"Costs are set equal to a constant times the relative turnover, where relative turnover is the ℓ1 norm of the change in portfolio weights.","card_quote":"Transaction costs can be set equal to a constant times the relative turnover. The relative turnover is the ℓ1 norm of wa −wa′.","meaning":"costs are part of the reported headline results"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The RL policy yields higher average daily rewards and annualized net returns than both the Greedy and Fixed strategies; e.g., Greedy’s max annualized net return is about 12% versus 22% for RL and 17% for Fixed 0.","kind":"performance","quote":"Greedy has a maximum annualized net return of only about the 12% compared to 22% and 17% for RL and Fixed 0."},{"finding":"RL consistently provides higher average reward than any of the fixed strategies across cost levels.","kind":"performance","quote":"On the other hand, RL consistently provides higher average reward than any of the fixed strategies."},{"finding":"In simulations, RL outperforms Greedy especially under large transaction costs, where fixed models can have negative rewards but RL remains positive.","kind":"performance","quote":"Overall, RL performs better than Greedy. For large transaction costs, some of the fixed models provide average negative rewards, while RL always has an average positive reward."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"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":"2026-11-14T18:25:04Z"},"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/"}