English
Related papers

Related papers: State Relevance for Off-Policy Evaluation

200 papers

We study the off-policy evaluation (OPE) problem in reinforcement learning with linear function approximation, which aims to estimate the value function of a target policy based on the offline data collected by a behavior policy. We propose…

Machine Learning · Computer Science 2022-01-05 Yifei Min , Tianhao Wang , Dongruo Zhou , Quanquan Gu

When data are clustered, common practice has become to do OLS and use an estimator of the covariance matrix of the OLS estimator that comes close to unbiasedness. In this paper we derive an estimator that is unbiased when the random-effects…

Econometrics · Economics 2022-06-22 Tom Boot , Gianmaria Niccodemi , Tom Wansbeek

Importance sampling, which involves sampling from a probability density function (PDF) proportional to the product of an importance weight function and a base PDF, is a powerful technique with applications in variance reduction, biased or…

Machine Learning · Computer Science 2025-02-10 Heasung Kim , Taekyun Lee , Hyeji Kim , Gustavo de Veciana

Off-policy evaluation (OPE) methods allow us to compute the expected reward of a policy by using the logged data collected by a different policy. OPE is a viable alternative to running expensive online A/B tests: it can speed up the…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Jacek Golebiowski , Philipp Schmidt , Ziawasch Abedjan , Artur Bekasov

We study off-policy evaluation (OPE) in partially observable environments with complex observations, with the goal of developing estimators whose guarantee avoids exponential dependence on the horizon. While such estimators exist for MDPs…

Machine Learning · Computer Science 2024-10-04 Yuheng Zhang , Nan Jiang

Likelihood-free inference involves inferring parameter values given observed data and a simulator model. The simulator is computer code which takes parameters, performs stochastic calculations, and outputs simulated data. In this work, we…

Computation · Statistics 2023-01-30 Dennis Prangle , Cecilia Viscardi

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…

Machine Learning · Computer Science 2025-06-26 Tatsuhiro Shimizu , Kazuki Kawamura , Takanori Muroi , Yusuke Narita , Kei Tateno , Takuma Udagawa , Yuta Saito

We consider an evolving system for which a sequence of observations is being made, with each observation revealing additional information about current and past states of the system. We suppose each observation is made without error, but…

Computation · Statistics 2021-03-10 Valentina Di Marco , Jonathan Keith

Direct fidelity estimation benefits from tailoring measurements to a fixed target, but the operator-aware shadow importance sampling (OASIS) method optimizes an outcome-wise linear-program surrogate rather than the exact worst-case variance…

Quantum Physics · Physics 2026-05-05 Hyunho Cha , Jungwoo Lee

While the classic off-policy evaluation (OPE) literature commonly assumes decision time points to be evenly spaced for simplicity, in many real-world scenarios, such as those involving user-initiated visits, decisions are made at…

Methodology · Statistics 2024-09-17 Xin Chen , Wenbin Lu , Shu Yang , Dipankar Bandyopadhyay

On-policy reinforcement learning (RL) algorithms are typically characterized as algorithms that perform policy updates using i.i.d. trajectories collected by the agent's current policy. However, after observing only a finite number of…

Machine Learning · Computer Science 2026-02-11 Nicholas E. Corrado , Josiah P. Hanna

Perhaps surprisingly, recent studies have shown probabilistic model likelihoods have poor specificity for out-of-distribution (OOD) detection and often assign higher likelihoods to OOD data than in-distribution data. To ameliorate this…

We discuss estimating the probability that the sum of nonnegative independent and identically distributed random variables falls below a given threshold, i.e., $\mathbb{P}(\sum_{i=1}^{N}{X_i} \leq \gamma)$, via importance sampling (IS). We…

Computation · Statistics 2021-10-04 Nadhir Ben Rached , Abdul-Lateef Haji-Ali , Gerardo Rubino , Raul Tempone

Importance sampling approximates expectations with respect to a target measure by using samples from a proposal measure. The performance of the method over large classes of test functions depends heavily on the closeness between both…

Computation · Statistics 2016-09-01 Daniel Sanz-Alonso

Reliability-oriented sensitivity analysis aims at combining both reliability and sensitivity analyses by quantifying the influence of each input variable of a numerical model on a quantity of interest related to its failure. In particular,…

Statistics Theory · Mathematics 2022-10-25 Julien Demange-Chryst , François Bachoc , Jérôme Morio

In different fields of applications including, but not limited to, behavioral, environmental, medical sciences and econometrics, the use of panel data regression models has become increasingly popular as a general framework for making…

Methodology · Statistics 2020-05-15 Beste Hamiye Beyaztas , Soutir Bandyopadhyay

We study the problem of off-policy evaluation (OPE) for episodic Partially Observable Markov Decision Processes (POMDPs) with continuous states. Motivated by the recently proposed proximal causal inference framework, we develop a…

Machine Learning · Statistics 2022-10-18 Rui Miao , Zhengling Qi , Xiaoke Zhang

We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal…

Machine Learning · Computer Science 2019-04-19 Yao Liu , Omer Gottesman , Aniruddh Raghu , Matthieu Komorowski , Aldo Faisal , Finale Doshi-Velez , Emma Brunskill

We study the problem of offline policy optimization in stochastic contextual bandit problems, where the goal is to learn a near-optimal policy based on a dataset of decision data collected by a suboptimal behavior policy. Rather than making…

Machine Learning · Computer Science 2023-09-28 Germano Gabbianelli , Gergely Neu , Matteo Papini

We introduce a new class of adaptive importance samplers leveraging adaptive optimisation tools, which we term AdaOAIS. We build on Optimised Adaptive Importance Samplers (OAIS), a class of techniques that adapt proposals to improve the…

Computation · Statistics 2024-10-28 Carlos A. C. C. Perello , Ömer Deniz Akyildiz