Off-Policy Evaluation and Learning for the Future under Non-Stationarity

• URL: http://arxiv.org/abs/2506.20417v1
• Date: Wed, 25 Jun 2025 13:31:46 GMT
• Title: Off-Policy Evaluation and Learning for the Future under Non-Stationarity
• Authors: Tatsuhiro Shimizu, Kazuki Kawamura, Takanori Muroi, Yusuke Narita, Kei Tateno, Takuma Udagawa, Yuta Saito,
• Abstract summary: We study the novel problem of future off-policy evaluation (F-OPE) and learning (F-OPL)<n>Our goal is often to estimate and optimize the policy value for the upcoming month using data collected by an old policy in the previous month.<n>Existing methods assume stationarity or depend on restrictive reward-modeling assumptions, leading to significant bias.
• Score: 18.657003350333298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study the novel problem of future off-policy evaluation (F-OPE) and learning (F-OPL) for estimating and optimizing the future value of policies in non-stationary environments, where distributions vary over time. In e-commerce recommendations, for instance, our goal is often to estimate and optimize the policy value for the upcoming month using data collected by an old policy in the previous month. A critical challenge is that data related to the future environment is not observed in the historical data. Existing methods assume stationarity or depend on restrictive reward-modeling assumptions, leading to significant bias. To address these limitations, we propose a novel estimator named \textit{\textbf{O}ff-\textbf{P}olicy Estimator for the \textbf{F}uture \textbf{V}alue (\textbf{\textit{OPFV}})}, designed for accurately estimating policy values at any future time point. The key feature of OPFV is its ability to leverage the useful structure within time-series data. While future data might not be present in the historical log, we can leverage, for example, seasonal, weekly, or holiday effects that are consistent in both the historical and future data. Our estimator is the first to exploit these time-related structures via a new type of importance weighting, enabling effective F-OPE. Theoretical analysis identifies the conditions under which OPFV becomes low-bias. In addition, we extend our estimator to develop a new policy-gradient method to proactively learn a good future policy using only historical data. Empirical results show that our methods substantially outperform existing methods in estimating and optimizing the future policy value under non-stationarity for various experimental setups.

Related papers

• PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data [36.6443700664411]
  Off-policy evaluation (OPE) methods aim to estimate the value of a new reinforcement learning (RL) policy prior to deployment.<n>We propose two approaches to construct valid confidence intervals for OPE when using data augmentation.
  arXiv  Detail & Related papers  (2025-07-26T21:51:15Z)
• Enhancing Mean-Reverting Time Series Prediction with Gaussian Processes: Functional and Augmented Data Structures in Financial Forecasting [0.0]
  We explore the application of Gaussian Processes (GPs) for predicting mean-reverting time series with an underlying structure. GPs offer the potential to forecast not just the average prediction but the entire probability distribution over a future trajectory. This is particularly beneficial in financial contexts, where accurate predictions alone may not suffice if incorrect volatility assessments lead to capital losses.
  arXiv  Detail & Related papers  (2024-02-23T06:09:45Z)
• When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective [64.73162159837956]
  evaluating the value of a hypothetical target policy with only a logged dataset is important but challenging. We propose DataCOPE, a data-centric framework for evaluating a target policy given a dataset. Our empirical analysis of DataCOPE in the logged contextual bandit settings using healthcare datasets confirms its ability to evaluate both machine-learning and human expert policies.
  arXiv  Detail & Related papers  (2023-11-23T17:13:37Z)
• Off-Policy Evaluation for Large Action Spaces via Policy Convolution [60.6953713877886]
  Policy Convolution family of estimators uses latent structure within actions to strategically convolve the logging and target policies. Experiments on synthetic and benchmark datasets demonstrate remarkable mean squared error (MSE) improvements when using PC.
  arXiv  Detail & Related papers  (2023-10-24T01:00:01Z)
• Uncertainty-Aware Instance Reweighting for Off-Policy Learning [63.31923483172859]
  We propose a Uncertainty-aware Inverse Propensity Score estimator (UIPS) for improved off-policy learning. Experiment results on synthetic and three real-world recommendation datasets demonstrate the advantageous sample efficiency of the proposed UIPS estimator.
  arXiv  Detail & Related papers  (2023-03-11T11:42:26Z)
• Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments [31.492146288630515]
  We introduce a variant of the doubly robust (DR) estimator, called the regression-assisted DR estimator, that can incorporate the past data without introducing a large bias. We empirically show that the new estimator improves estimation for the current and future policy values, and provides a tight and valid interval estimation in several nonstationary recommendation environments.
  arXiv  Detail & Related papers  (2023-02-23T01:17:21Z)
• Lifelong Hyper-Policy Optimization with Multiple Importance Sampling Regularization [40.17392342387002]
  We propose an approach which learns a hyper-policy, whose input is time, that outputs the parameters of the policy to be queried at that time. This hyper-policy is trained to maximize the estimated future performance, efficiently reusing past data by means of importance sampling. We empirically validate our approach, in comparison with state-of-the-art algorithms, on realistic environments.
  arXiv  Detail & Related papers  (2021-12-13T13:09:49Z)
• Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits [5.144809478361604]
  We improve the doubly robust (DR) estimator by adaptively weighting observations to control its variance. We provide empirical evidence for our estimator's improved accuracy and inferential properties relative to existing alternatives.
  arXiv  Detail & Related papers  (2021-06-03T17:54:44Z)
• Distributionally Robust Batch Contextual Bandits [20.667213458836734]
  Policy learning using historical observational data is an important problem that has found widespread applications. Existing literature rests on the crucial assumption that the future environment where the learned policy will be deployed is the same as the past environment. In this paper, we lift this assumption and aim to learn a distributionally robust policy with incomplete observational data.
  arXiv  Detail & Related papers  (2020-06-10T03:11:40Z)
• Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies [80.42316902296832]
  We study the estimation of policy value and gradient of a deterministic policy from off-policy data when actions are continuous. In this setting, standard importance sampling and doubly robust estimators for policy value and gradient fail because the density ratio does not exist. We propose several new doubly robust estimators based on different kernelization approaches.
  arXiv  Detail & Related papers  (2020-06-06T15:52:05Z)
• Optimizing for the Future in Non-Stationary MDPs [52.373873622008944]
  We present a policy gradient algorithm that maximizes a forecast of future performance. We show that our algorithm, called Prognosticator, is more robust to non-stationarity than two online adaptation techniques.
  arXiv  Detail & Related papers  (2020-05-17T03:41:19Z)
• Minimax-Optimal Off-Policy Evaluation with Linear Function Approximation [49.502277468627035]
  This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history.
  arXiv  Detail & Related papers  (2020-02-21T19:20:57Z)

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.