English
Related papers

Related papers: On Minimax Optimal Offline Policy Evaluation

200 papers

We study episodic two-player zero-sum Markov games (MGs) in the offline setting, where the goal is to find an approximate Nash equilibrium (NE) policy pair based on a dataset collected a priori. When the dataset does not have uniform…

Machine Learning · Computer Science 2023-01-02 Han Zhong , Wei Xiong , Jiyuan Tan , Liwei Wang , Tong Zhang , Zhaoran Wang , Zhuoran Yang

Offline reinforcement learning, wherein one uses off-policy data logged by a fixed behavior policy to evaluate and learn new policies, is crucial in applications where experimentation is limited such as medicine. We study the estimation of…

Machine Learning · Computer Science 2020-06-09 Nathan Kallus , Masatoshi Uehara

We study sequential decision making in environments where rewards are only partially observed, but can be modeled as a function of observed contexts and the chosen action by the decision maker. This setting, known as contextual bandits,…

Methodology · Statistics 2015-03-11 Miroslav Dudík , Dumitru Erhan , John Langford , Lihong Li

Designing effective model-based reinforcement learning algorithms is difficult because the ease of data generation must be weighed against the bias of model-generated data. In this paper, we study the role of model usage in policy…

Machine Learning · Computer Science 2021-11-30 Michael Janner , Justin Fu , Marvin Zhang , Sergey Levine

The stochastic multi-armed bandit (MAB) problem is a common model for sequential decision problems. In the standard setup, a decision maker has to choose at every instant between several competing arms, each of them provides a scalar random…

Machine Learning · Statistics 2021-10-27 Asaf Cassel , Shie Mannor , Assaf Zeevi

Evaluating novel contextual bandit policies using logged data is crucial in applications where exploration is costly, such as medicine. But it usually relies on the assumption of no unobserved confounders, which is bound to fail in…

Machine Learning · Statistics 2019-08-07 Andrew Bennett , Nathan Kallus

We provide a comparative study of several widely used off-policy estimators (Empirical Average, Basic Importance Sampling and Normalized Importance Sampling), detailing the different regimes where they are individually suboptimal. We then…

Machine Learning · Statistics 2019-01-30 Thomas Nedelec , Nicolas Le Roux , Vianney Perchet

We address online linear optimization problems when the possible actions of the decision maker are represented by binary vectors. The regret of the decision maker is the difference between her realized loss and the best loss she would have…

Machine Learning · Computer Science 2013-04-02 Jean-Yves Audibert , Sébastien Bubeck , Gábor Lugosi

Methods for offline A/B testing and counterfactual learning are seeing rapid adoption in search and recommender systems, since they allow efficient reuse of existing log data. However, there are fundamental limits to using existing log data…

Machine Learning · Computer Science 2022-02-04 Aaron David Tucker , Thorsten Joachims

Accurately evaluating new policies (e.g. ad-placement models, ranking functions, recommendation functions) is one of the key prerequisites for improving interactive systems. While the conventional approach to evaluation relies on online A/B…

Machine Learning · Computer Science 2017-06-27 Aman Agarwal , Soumya Basu , Tobias Schnabel , Thorsten Joachims

In bandit best-arm identification, an algorithm is tasked with finding the arm with highest mean reward with a specified accuracy as fast as possible. We study multi-fidelity best-arm identification, in which the algorithm can choose to…

Machine Learning · Computer Science 2025-05-27 Riccardo Poiani , Rémy Degenne , Emilie Kaufmann , Alberto Maria Metelli , Marcello Restelli

Learning from human feedback has been central to recent advances in artificial intelligence and machine learning. Since the collection of human feedback is costly, a natural question to ask is if the new feedback always needs to collected.…

Machine Learning · Computer Science 2024-06-17 Aniruddha Bhargava , Lalit Jain , Branislav Kveton , Ge Liu , Subhojyoti Mukherjee

We investigate the problem of jointly testing a pair of composite hypotheses and, depending on the test result, estimating a random parameter under distributional uncertainties. Specifically, it is assumed that the distribution of the data…

Signal Processing · Electrical Eng. & Systems 2026-04-27 Dominik Reinhard , Michael Fauß , Abdelhak M. Zoubir

Learning effective contextual-bandit policies from past actions of a deployed system is highly desirable in many settings (e.g. voice assistants, recommendation, search), since it enables the reuse of large amounts of log data.…

Machine Learning · Computer Science 2020-06-18 Noveen Sachdeva , Yi Su , Thorsten Joachims

In this paper, we study the contextual multinomial logit (MNL) bandit problem in which a learning agent sequentially selects an assortment based on contextual information, and user feedback follows an MNL choice model. There has been a…

Machine Learning · Statistics 2025-10-17 Joongkyu Lee , Min-hwan Oh

Off-policy learning (OPL) in contextual bandits aims to learn a decision-making policy that maximizes the target rewards by using only historical interaction data collected under previously developed policies. Unfortunately, when rewards…

Machine Learning · Computer Science 2025-06-18 Rikiya Takehi , Masahiro Asami , Kosuke Kawakami , Yuta Saito

We provide theoretical investigations into off-policy evaluation in reinforcement learning using function approximators for (marginalized) importance weights and value functions. Our contributions include: (1) A new estimator, MWL, that…

Machine Learning · Computer Science 2020-10-08 Masatoshi Uehara , Jiawei Huang , Nan Jiang

We study the stochastic linear bandit problem with multiple arms over $T$ rounds, where the covariate dimension $d$ may exceed $T$, but each arm-specific parameter vector is $s$-sparse. We begin by analyzing the sequential estimation…

Statistics Theory · Mathematics 2025-05-26 Jingyu Liu , Yanglei Song

Choosing optimal (or at least better) policies is an important problem in domains from medicine to education to finance and many others. One approach to this problem is through controlled experiments/trials - but controlled experiments are…

Artificial Intelligence · Computer Science 2018-02-26 Onur Atan , William R. Zame , M van der Schaar

We study the stochastic multi-armed bandit (MAB) problem in the presence of side-observations across actions that occur as a result of an underlying network structure. In our model, a bipartite graph captures the relationship between…

Machine Learning · Computer Science 2017-07-14 Swapna Buccapatnam , Fang Liu , Atilla Eryilmaz , Ness B. Shroff
‹ Prev 1 8 9 10 Next ›