Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning

• URL: http://arxiv.org/abs/2608.24858v1
• Date: Tue, 25 Aug 2026 17:44:02 GMT
• Title: Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning
• Abstract summary: We introduce isotonic Bellman calibration, a one-dimensional, model-agnostic post-processing method.<n>Method corrects estimate's scale and shape by applying fitted occupancy-ratio evaluation (FORE) over a one-dimensional class of nondecreasing transformations.<n>We derive a calibration-refinement bound showing that any fitted ratio with small calibration error performs nearly as well as the best post-processing.
• Score: 40.322273308230606
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Marginalized importance weighting evaluates a target policy by reweighting offline state-action samples with its discounted occupancy ratio, characterized by an adjoint Bellman equation. Existing minimax, primal-dual, and fitted fixed-point estimators can leave residual occupancy-balance violations because of function-class approximation, regularization, or incomplete optimization. These violations are difficult to diagnose and reduce because the objectives generally lack a direct supervised validation loss for hyperparameter tuning, model selection, and early stopping. We introduce isotonic Bellman calibration, a one-dimensional, model-agnostic post-processing method that reduces these violations while preserving the ranking information in any initial occupancy-ratio estimate. The method corrects the estimate's scale and shape by applying fitted occupancy-ratio evaluation (FORE) over a one-dimensional class of nondecreasing transformations. We characterize Bellman calibration as a conditional fixed-point property equivalent to occupancy-balance against every test function of the calibrated ratio. More generally, we derive a calibration-refinement bound showing that any fitted ratio with small calibration error performs nearly as well as the best post-processing based on its fitted values. For isotonic Bellman calibration, we establish finite-sample calibration guarantees and a KL oracle inequality relative to the best monotone transformation of the initial estimate. Consequently, isotonic Bellman calibration achieves small calibration error and KL risk within statistical error of the best monotone correction, with guarantees for downstream target-occupancy functionals, including policy-value estimation.

Related papers

• Bellman Calibration for V-Learning in Offline Reinforcement Learning [40.322273308230606]
  We introduce Iterated Bellman, a simple, model-agnostic, post-hoc procedure for calibrating off-policy value predictions.<n>We adapt classical histogram and isotonic calibration to the dynamic, counterfactual setting.<n>This yields a one-dimensional fitted value scheme that can be applied to any value estimator.
  arXiv  Detail & Related papers  (2025-12-29T18:52:18Z)
• Rethinking Early Stopping: Refine, Then Calibrate [49.966899634962374]
  We present a novel variational formulation of the calibration-refinement decomposition.<n>We provide theoretical and empirical evidence that calibration and refinement errors are not minimized simultaneously during training.
  arXiv  Detail & Related papers  (2025-01-31T15:03:54Z)
• Parametric $ρ$-Norm Scaling Calibration [8.583311125489942]
  Output uncertainty indicates whether the probabilistic properties reflect objective characteristics of the model output.<n>We introduce a post-processing parametric calibration method, $rho$-Norm Scaling, which expands the calibrator expression and mitigates overconfidence due to excessive amplitude.
  arXiv  Detail & Related papers  (2024-12-19T10:42:11Z)
• Orthogonal Causal Calibration [55.28164682911196]
  We develop general algorithms for reducing the task of causal calibration to that of calibrating a standard (non-causal) predictive model.<n>Our results are exceedingly general, showing that essentially any existing calibration algorithm can be used in causal settings.
  arXiv  Detail & Related papers  (2024-06-04T03:35:25Z)
• Towards Certification of Uncertainty Calibration under Adversarial Attacks [96.48317453951418]
  We show that attacks can significantly harm calibration, and thus propose certified calibration as worst-case bounds on calibration under adversarial perturbations.<n>We propose novel calibration attacks and demonstrate how they can improve model calibration through textitadversarial calibration training
  arXiv  Detail & Related papers  (2024-05-22T18:52:09Z)
• Consistent and Asymptotically Unbiased Estimation of Proper Calibration Errors [23.819464242327257]
  We propose a method that allows consistent estimation of all proper calibration errors and refinement terms. We prove the relation between refinement and f-divergences, which implies information monotonicity in neural networks. Our experiments validate the claimed properties of the proposed estimator and suggest that the selection of a post-hoc calibration method should be determined by the particular calibration error of interest.
  arXiv  Detail & Related papers  (2023-12-14T01:20:08Z)
• Calibration by Distribution Matching: Trainable Kernel Calibration Metrics [56.629245030893685]
  We introduce kernel-based calibration metrics that unify and generalize popular forms of calibration for both classification and regression. These metrics admit differentiable sample estimates, making it easy to incorporate a calibration objective into empirical risk minimization. We provide intuitive mechanisms to tailor calibration metrics to a decision task, and enforce accurate loss estimation and no regret decisions.
  arXiv  Detail & Related papers  (2023-10-31T06:19:40Z)
• Localized Calibration: Metrics and Recalibration [133.07044916594361]
  We propose a fine-grained calibration metric that spans the gap between fully global and fully individualized calibration. We then introduce a localized recalibration method, LoRe, that improves the LCE better than existing recalibration methods.
  arXiv  Detail & Related papers  (2021-02-22T07:22:12Z)

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.