English
Related papers

Related papers: Off-Policy Evaluation of Bandit Algorithm from Dep…

200 papers

Contextual multi-armed bandits are classical models in reinforcement learning for sequential decision-making associated with individual information. A widely-used policy for bandits is Thompson Sampling, where samples from a data-driven…

Machine Learning · Statistics 2021-11-30 Hongju Park , Mohamad Kazem Shirani Faradonbeh

Off-policy evaluation (OPE) is widely applied in sectors such as pharmaceuticals and e-commerce to evaluate the efficacy of novel products or policies from offline datasets. This paper introduces a causal deepset framework that relaxes…

Machine Learning · Statistics 2024-07-26 Runpeng Dai , Jianing Wang , Fan Zhou , Shikai Luo , Zhiwei Qin , Chengchun Shi , Hongtu Zhu

In applying reinforcement learning (RL) to high-stakes domains, quantitative and qualitative evaluation using observational data can help practitioners understand the generalization performance of new policies. However, this type of…

Machine Learning · Computer Science 2023-10-27 Shengpu Tang , Jenna Wiens

We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized) actions, and (nonnegative) rewards. A common goal is to…

Machine Learning · Computer Science 2019-01-16 Yifei Ma , Yu-Xiang Wang , Balakrishnan , Narayanaswamy

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

Policy gradient methods in reinforcement learning update policy parameters by taking steps in the direction of an estimated gradient of policy value. In this paper, we consider the statistically efficient estimation of policy gradients from…

Machine Learning · Statistics 2020-02-21 Nathan Kallus , Masatoshi Uehara

We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\pi_e$, using a fixed dataset, $\mathcal{D}$, collected by one or more policies…

Machine Learning · Computer Science 2022-12-16 Brahma S. Pavse , Josiah P. Hanna

Off-policy learning methods seek to derive an optimal policy directly from a fixed dataset of prior interactions. This objective presents significant challenges, primarily due to the inherent distributional shift and value function…

Machine Learning · Computer Science 2026-02-03 Arip Asadulaev , Maksim Bobrin , Salem Lahlou , Dmitry Dylov , Fakhri Karray , Martin Takac

Bandit algorithms sequentially accumulate data using adaptive sampling policies, offering flexibility for real-world applications. However, excessive sampling can be costly, motivating the devolopment of early stopping methods and reliable…

Statistics Theory · Mathematics 2025-02-06 Zihan Cui

Addressing such diverse ends as safety alignment with human preferences, and the efficiency of learning, a growing line of reinforcement learning research focuses on risk functionals that depend on the entire distribution of returns. Recent…

Machine Learning · Computer Science 2022-09-22 Audrey Huang , Liu Leqi , Zachary Chase Lipton , Kamyar Azizzadenesheli

We study the problem of model selection in batch policy optimization: given a fixed, partial-feedback dataset and $M$ model classes, learn a policy with performance that is competitive with the policy derived from the best model class. We…

Machine Learning · Computer Science 2021-12-24 Jonathan N. Lee , George Tucker , Ofir Nachum , Bo Dai

We study distributional off-policy evaluation (OPE), of which the goal is to learn the distribution of the return for a target policy using offline data generated by a different policy. The theoretical foundation of many existing work…

Machine Learning · Statistics 2025-03-13 Sungee Hong , Zhengling Qi , Raymond K. W. Wong

Multi-armed Bandits (MABs) are increasingly employed in online platforms and e-commerce to optimize decision making for personalized user experiences. In this work, we focus on the Contextual Bandit problem with linear rewards, under…

Machine Learning · Computer Science 2024-09-17 Rowan Swiers , Subash Prabanantham , Andrew Maher

In this work, we consider the problem of estimating a behaviour policy for use in Off-Policy Policy Evaluation (OPE) when the true behaviour policy is unknown. Via a series of empirical studies, we demonstrate how accurate OPE is strongly…

Machine Learning · Computer Science 2018-07-11 Aniruddh Raghu , Omer Gottesman , Yao Liu , Matthieu Komorowski , Aldo Faisal , Finale Doshi-Velez , Emma Brunskill

Motivated by recommendation problems in music streaming platforms, we propose a nonstationary stochastic bandit model in which the expected reward of an arm depends on the number of rounds that have passed since the arm was last pulled.…

Machine Learning · Statistics 2020-02-20 Leonardo Cella , Nicolò Cesa-Bianchi

For an autonomous agent, executing a poor policy may be costly or even dangerous. For such agents, it is desirable to determine confidence interval lower bounds on the performance of any given policy without executing said policy. Current…

Artificial Intelligence · Computer Science 2018-09-25 Josiah P. Hanna , Peter Stone , Scott Niekum

We introduce a novel doubly-robust (DR) off-policy evaluation (OPE) estimator for Markov decision processes, DRUnknown, designed for situations where both the logging policy and the value function are unknown. The proposed estimator…

Machine Learning · Statistics 2024-04-03 Kyungbok Lee , Myunghee Cho Paik

This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities", we…

Methodology · Statistics 2024-08-20 Zeyu Bian , Chengchun Shi , Zhengling Qi , Lan Wang

Bandit algorithms are widely used in sequential decision problems to maximize the cumulative reward. One potential application is mobile health, where the goal is to promote the user's health through personalized interventions based on user…

Machine Learning · Statistics 2022-08-23 Gi-Soo Kim , Hyun-Joon Yang , Jane P. Kim

Model-based methods have recently shown great potential for off-policy evaluation (OPE); offline trajectories induced by behavioral policies are fitted to transitions of Markov decision processes (MDPs), which are used to rollout simulated…

Machine Learning · Computer Science 2023-02-06 Qitong Gao , Ge Gao , Min Chi , Miroslav Pajic