Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity

• URL: http://arxiv.org/abs/2605.03393v1
• Date: Tue, 05 May 2026 06:08:54 GMT
• Title: Adaptive Estimation and Optimal Control in Offline Contextual MDPs without Stationarity
• Abstract summary: We introduce a new approach towards adaptive estimation and cost optimization of contextual MDPs.<n>We achieve this by overcoming the key technical challenges evolving from the endogenous properties of contextual MDPs.<n>Our guarantees are established under complete generality by utilizing the relatively recent and powerful statistical technique of $T$-estimation.
• Score: 4.686525329317328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contextual MDPs are powerful tools with wide applicability in areas from biostatistics to machine learning. However, specializing them to offline datasets has been challenging due to a lack of robust, theoretically backed methods. Our work tackles this problem by introducing a new approach towards adaptive estimation and cost optimization of contextual MDPs. This estimator, to the best of our knowledge, is the first of its kind, and is endowed with strong optimality guarantees. We achieve this by overcoming the key technical challenges evolving from the endogenous properties of contextual MDPs; such as non-stationarity, or model irregularity. Our guarantees are established under complete generality by utilizing the relatively recent and powerful statistical technique of $T$-estimation (Baraud, 2011). We first provide a procedure for selecting an estimator given a sample from a contextual MDP and use it to derive oracle risk bounds under two distinct, but nevertheless meaningful, loss functions. We then consider the problem of determining the optimal control with the aid of the aforementioned density estimate and provide finite sample guarantees for the cost function.

Related papers

• Robust Peak-cost Constrained Reinforcement Learning [10.897248153175935]
  We study robust peak-cost constrained reinforcement learning (RP-CRL)<n>The objective is to maximize expected reward while controlling the maximum cost encountered along a trajectory.<n>We show that, unlike standard CMDPs, peak-cost constrained MDPs may not admit zero duality gap.
  arXiv  Detail & Related papers  (2026-07-16T21:00:50Z)
• Learning Polyhedral Conformal Sets for Robust Optimization [10.504036065018216]
  We propose a decision-aware conformal framework that learns uncertainty sets tailored to robust optimization objectives.<n>Our approach parameterizes a flexible family of polyhedral sets via data-driven hyperplanes and learns their geometry by directly minimizing the induced robust loss.<n>We provide finite-sample coverage guarantees and bounds on the sub-optimality gap to an oracle decision.
  arXiv  Detail & Related papers  (2026-05-08T21:39:41Z)
• Reliability-Aware Determinantal Point Processes for Robust Informative Data Selection in Large Language Models [6.463509584149428]
  We introduce ProbDPP, a reliability-aware implementation of k-DPP that accounts for probabilistic data access.<n>We frame this reliability-aware diversity as a semi-bandit problem and propose a UCB-style algorithm to efficiently learn unknown reliability online.
  arXiv  Detail & Related papers  (2026-01-31T20:14:33Z)
• Labels or Preferences? Budget-Constrained Learning with Human Judgments over AI-Generated Outputs [17.028710603629026]
  We show how to optimally allocate a fixed annotation budget between ground-truth labels and pairwise preferences in AI.<n>We introduce Preference-Calibrated Active Learning (PCAL), a novel robustness method that learns optimal data acquisition strategy.<n>This work provides a principled and statistically efficient approach for budget-constrained learning in modern AI.
  arXiv  Detail & Related papers  (2026-01-19T23:23:29Z)
• Reliable LLM-Based Edge-Cloud-Expert Cascades for Telecom Knowledge Systems [54.916243942641444]
  Large language models (LLMs) are emerging as key enablers of automation in domains such as telecommunications.<n>We study an edge-cloud-expert cascaded LLM-based knowledge system that supports decision-making through a question-and-answer pipeline.
  arXiv  Detail & Related papers  (2025-12-23T03:10:09Z)
• On the Optimality of Tracking Fisher Information in Adaptive Testing with Stochastic Binary Responses [3.491999371287298]
  We study the problem of estimating a continuous ability parameter from sequential binary responses.<n>We propose a simple algorithm that adaptively selects questions to maximize Fisher information.<n>We prove that this Fisher-tracking strategy achieves optimal performance in both fixed-confidence and fixed-budget regimes.
  arXiv  Detail & Related papers  (2025-10-09T07:10:00Z)
• Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality [53.525547349715595]
  We propose a novel primal-only algorithm called Rectified Robust Policy Optimization (RRPO)<n>RRPO operates directly on the primal problem without relying on dual formulations.<n>We show convergence to an approximately optimal feasible policy with complexity matching the best-known lower bound.
  arXiv  Detail & Related papers  (2025-08-24T16:59:38Z)
• Distributionally Robust Optimization with Adversarial Data Contamination [49.89480853499918]
  We focus on optimizing Wasserstein-1 DRO objectives for generalized linear models with convex Lipschitz loss functions.<n>Our primary contribution lies in a novel modeling framework that integrates robustness against training data contamination with robustness against distributional shifts.<n>This work establishes the first rigorous guarantees, supported by efficient computation, for learning under the dual challenges of data contamination and distributional shifts.
  arXiv  Detail & Related papers  (2025-07-14T18:34:10Z)
• End-to-End Learning for Fair Multiobjective Optimization Under Uncertainty [55.04219793298687]
  The Predict-Then-Forecast (PtO) paradigm in machine learning aims to maximize downstream decision quality. This paper extends the PtO methodology to optimization problems with nondifferentiable Ordered Weighted Averaging (OWA) objectives. It shows how optimization of OWA functions can be effectively integrated with parametric prediction for fair and robust optimization under uncertainty.
  arXiv  Detail & Related papers  (2024-02-12T16:33:35Z)
• Log Barriers for Safe Black-box Optimization with Application to Safe Reinforcement Learning [72.97229770329214]
  We introduce a general approach for seeking high dimensional non-linear optimization problems in which maintaining safety during learning is crucial. Our approach called LBSGD is based on applying a logarithmic barrier approximation with a carefully chosen step size. We demonstrate the effectiveness of our approach on minimizing violation in policy tasks in safe reinforcement learning.
  arXiv  Detail & Related papers  (2022-07-21T11:14:47Z)
• Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning [52.74071439183113]
  We study the predict-then-optimize framework in the context of sequential decision problems (formulated as MDPs) solved via reinforcement learning. Two significant computational challenges arise in applying decision-focused learning to MDPs.
  arXiv  Detail & Related papers  (2021-06-06T23:53:31Z)
• An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes [0.0]
  Exploitation vs Caution (EvC) is a paradigm that elegantly incorporates model uncertainty abiding by the Bayesian formalism. We validate EvC with state-of-the-art approaches in different discrete, yet simple, environments offering a fair variety of MDP classes. In the tested scenarios EvC manages to select robust policies and hence stands out as a useful tool for practitioners.
  arXiv  Detail & Related papers  (2021-05-27T20:12:20Z)
• Data-Driven Robust Optimization using Unsupervised Deep Learning [0.0]
  We show that a trained neural network can be integrated into a robust optimization model by formulating the adversarial problem as a convex mixed-integer program. We find that this approach outperforms a similar approach using kernel-based support vector sets.
  arXiv  Detail & Related papers  (2020-11-19T11:06:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.