{"paper_id":"2512.14991","title":"Adaptive Partitioning and Learning for Stochastic Control of Diffusion Processes","authors":["Hanqing Jin","Renyuan Xu","Yanzhao Yang"],"paper_date":"2025-12-17","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2512.14991v1","page_url":"https://thequant.space/flowcharts/adaptive-partitioning-and-learning-for-stochastic-control-of/","scores":{"empirical_rigor":5,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a model‑based reinforcement learning algorithm that adaptively partitions the joint state‑action space, maintains drift, volatility and reward estimators within each partition, and selects actions via an upper confidence bound on the constructed Q‑function.","quote":"To overcome the challenges of continuous and high-dimensional domains, we introduce a model-based algorithm that adaptively partitions the joint state-action space. The algorithm maintains estimators of drift, volatility, and rewards within each partition, refining the discretization whenever estimation bias exceeds statistical confidence.","summary":"We study reinforcement learning for controlled diffusion processes with unbounded continuous state spaces, bounded continuous actions, and polynomially growing rewards: settings that arise naturally in finance, economics, and operations research. To overcome the challenges of continuous and…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The drift µ_h, volatility σ_h and mean reward \\bar R_h are locally Lipschitz continuous in state and action.","type":"model","stated":"explicit","quote":"Assume there exists constants ℓµ, ℓσ > 0, m ∈N and L0 > 0 such that for all h ∈[H −1], x1, x2 ∈RdS, and a1, a2 ∈A, it holds that: ∥µh(x1, a1) −µh(x2, a2)∥ ≤ ℓµ \u0010 ∥x1 −x2∥+ ∥a1 −a2∥ \u0011 , ∥σh(x1, a1) −σh(x1, a2)∥ ≤ ℓσ \u0010 ∥x1 −x2∥+ ∥a1 −a2∥ \u0011 , max h∈[H−1]{∥µh(0, 0)∥, ∥σh(0, 0)∥} ≤ L0.","support":"full"},{"assumption":"The reward distributions have sub‑Gaussian tail decay.","type":"statistical","stated":"explicit","quote":"In addition, assume that the reward distribution has sub-Gaussian tail decay, i.e., there exists a known constant θ > 0 such that ∀x ∈RdS, a ∈A, λ1 ∈R, and h ∈[H]: Erh∼Rh(x,a) h exp \u0010 λ1(rh −¯Rh(x, a)) \u0011i ≤e θλ2 1 2 .","support":"full"},{"assumption":"The volatility matrices satisfy a uniform ellipticity condition (σ_h σ_h^⊤ ≻ λ I).","type":"model","stated":"explicit","quote":"In addition, assume the following elliptic condition, i.e., there exists a constant λ > 0 such that ∀x ∈RdS, a ∈A, and h ∈[H −1]: σh(x, a)σh(x, a)⊤≻λIdS.","support":"full"},{"assumption":"The initial state distribution has finite p‑th moment with p^2 larger than a specified polynomial in dimensions and reward order.","type":"data","stated":"explicit","quote":"Assume that there exists p ∈N with p2 > (m + 1)2(dS + dA + 2) + (m + 1)(2dS + 2m + 4), such that the initial state X1 = ξ of the diffusion process in (2.1) satisfies: Eξ∼Ξ[∥ξ∥p] < +∞, The assumption that p2 > (m+1)2(dS +dA +2)+(m+1)(2dS +2m+4) ensures that the initial distribution is well behaved.","support":"full"},{"assumption":"The state transition follows a discretized controlled diffusion: X_{h+1} - X_h = µ_h Δ + σ_h B_h √Δ with Gaussian noise B_h.","type":"model","stated":"explicit","quote":"Mathematically, for h ∈[H −1], the state process follows: Xh+1 −Xh = µh(Xh, Ah)∆+ σh(Xh, Ah)Bh √ ∆, (2.1) X1 = ξ, where ∆> 0 is the time-increment between two consecutive time stamps, Bh are i.i.d. samples from the multi-variate Gaussian distribution N(0, IdS) and ξ is independently sampled from an initial distribution Ξ. Clearly, for non-degenerate σh(x, a), we have Th(·|x, a) = N \u0010 µh(x, a)∆, Σh(x, a)∆ \u0011 , where","support":"full"},{"assumption":"The state‑action space is initially partitioned into hypercubes of fixed diameter D > 0.","type":"other","stated":"explicit","quote":"We first partition the entire state-action space RdS ×A into (closed) hypercubes of fixed diameter D > 0.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"synthetic high‑dimensional multi‑asset mean‑variance portfolio selection problems","provider":null,"kind":"synthetic","access":"unknown","period":null,"universe":null,"quote":"Finally, we validate the effectiveness of our approach through numerical experiments, including applications to high-dimensional problems such as multi-asset mean-variance portfolio selection.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"synthetic"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"evidence_card","rule":"R2","candidates":{"front_matter":"unclear","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"The algorithm achieves a regret bound of order \\tilde O(H K^{1-p/2-(m+1)^2(z_{max,c}+2)^{- (m+1)(2d_S+2m+4)} p(p+m+1)(z_{max,c}+2)+p(2d_S+2m+4)}) where H is horizon, K episodes, p moments, m reward growth order, d_S state dimension and z_{max,c} worst‑case zoo","kind":"theoretical","quote":"Mathematically, we show that the proposed algorithm achieves a regret of order ˜O(HK 1−p2−(m+1)2(zmax,c+2)−(m+1)(2dS +2m+4) p(p+m+1)(zmax,c+2)+p(2dS +2m+4) ), with H the horizon of the problem, K the number of episodes, p the highest bounded moments for the initial state distribution, m + 1 the order of reward polynomial growth, dS the dimension of state space and zmax,c the worst-case zooming dimension over the","support":"full"},{"finding":"The regret bounds specialize to existing results for bounded settings, showing the method extends classical rates to unbounded diffusion processes.","kind":"theoretical","quote":"The bounds recover existing results for bounded settings as a special case, while extending theoretical guarantees to a broader class of diffusion-type problems.","support":"full"},{"finding":"Numerical experiments on high‑dimensional problems such as multi‑asset mean‑variance portfolio selection demonstrate the effectiveness of the adaptive partitioning approach.","kind":"performance","quote":"Finally, we validate the effectiveness of our approach through numerical experiments, including applications to high-dimensional problems such as multi-asset mean-variance portfolio selection.","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":8,"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":2,"extracted_at":"2026-11-14T19:44:55Z"},"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/"}