English
Related papers

Related papers: Off-Policy Risk Assessment in Contextual Bandits

200 papers

Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…

Machine Learning · Computer Science 2021-02-15 Ron Dorfman , Idan Shenfeld , Aviv Tamar

Reinforcement learning algorithms have had tremendous successes in online learning settings. However, these successes have relied on low-stakes interactions between the algorithmic agent and its environment. In many settings where RL could…

Machine Learning · Computer Science 2020-06-05 James Bannon , Brad Windsor , Wenbo Song , Tao Li

We consider a partial-feedback variant of the well-studied online PCA problem where a learner attempts to predict a sequence of $d$-dimensional vectors in terms of a quadratic loss, while only having limited feedback about the environment's…

Machine Learning · Computer Science 2019-02-11 Wojciech Kotłowski , Gergely Neu

A great variety of off-policy learning algorithms exist in the literature, and new breakthroughs in this area continue to be made, improving theoretical understanding and yielding state-of-the-art reinforcement learning algorithms. In this…

Machine Learning · Computer Science 2020-07-31 Mark Rowland , Will Dabney , Rémi Munos

Offline reinforcement learning (RL) looks at learning how to optimally solve tasks using a fixed dataset of interactions from the environment. Many off-policy algorithms developed for online learning struggle in the offline setting as they…

Machine Learning · Computer Science 2025-03-18 Natinael Solomon Neggatu , Jeremie Houssineau , Giovanni Montana

In this paper, we present refined probabilistic bounds on empirical reward estimates for off-policy learning in bandit problems. We build on the PAC-Bayesian bounds from Seldin et al. (2010) and improve on their results using a new…

Machine Learning · Statistics 2025-02-18 Amaury Gouverneur , Tobias J. Oechtering , Mikael Skoglund

The dynamic portfolio optimization problem in finance frequently requires learning policies that adhere to various constraints, driven by investor preferences and risk. We motivate this problem of finding an allocation policy within a…

Artificial Intelligence · Computer Science 2020-12-23 Nymisha Bandi , Theja Tulabandhula

We study high-confidence behavior-agnostic off-policy evaluation in reinforcement learning, where the goal is to estimate a confidence interval on a target policy's value, given only access to a static experience dataset collected by…

Machine Learning · Computer Science 2020-10-23 Bo Dai , Ofir Nachum , Yinlam Chow , Lihong Li , Csaba Szepesvári , Dale Schuurmans

We propose a risk-averse statistical learning framework wherein the performance of a learning algorithm is evaluated by the conditional value-at-risk (CVaR) of losses rather than the expected loss. We devise algorithms based on stochastic…

Machine Learning · Computer Science 2020-02-17 Tasuku Soma , Yuichi Yoshida

When faced with sequential decision-making problems, it is often useful to be able to predict what would happen if decisions were made using a new policy. Those predictions must often be based on data collected under some previously used…

Machine Learning · Computer Science 2021-11-03 Yash Chandak , Scott Niekum , Bruno Castro da Silva , Erik Learned-Miller , Emma Brunskill , Philip S. Thomas

Many offline reinforcement learning algorithms are underpinned by $f$-divergence regularization, but their sample complexity *defined with respect to regularized objectives* still lacks tight analyses, especially in terms of concrete data…

Machine Learning · Computer Science 2026-02-27 Qingyue Zhao , Kaixuan Ji , Heyang Zhao , Tong Zhang , Quanquan Gu

Contextual bandits are widely used in industrial personalization systems. These online learning frameworks learn a treatment assignment policy in the presence of treatment effects that vary with the observed contextual features of the…

Machine Learning · Computer Science 2022-05-11 Claudia Roberts , Maria Dimakopoulou , Qifeng Qiao , Ashok Chandrashekhar , Tony Jebara

We study a constrained contextual linear bandit setting, where the goal of the agent is to produce a sequence of policies, whose expected cumulative reward over the course of $T$ rounds is maximum, and each has an expected cost below a…

Machine Learning · Computer Science 2020-06-20 Aldo Pacchiano , Mohammad Ghavamzadeh , Peter Bartlett , Heinrich Jiang

Off-policy learning plays a pivotal role in optimizing and evaluating policies prior to the online deployment. However, during the real-time serving, we observe varieties of interventions and constraints that cause inconsistency between the…

Machine Learning · Computer Science 2022-03-01 Da Xu , Yuting Ye , Chuanwei Ruan , Bo Yang

A major challenge in contextual bandits is to design general-purpose algorithms that are both practically useful and theoretically well-founded. We present a new technique that has the empirical and computational advantages of…

Machine Learning · Computer Science 2018-03-06 Dylan J. Foster , Alekh Agarwal , Miroslav Dudík , Haipeng Luo , Robert E. Schapire

We study the offline contextual bandit problem, where we aim to acquire an optimal policy using observational data. However, this data usually contains two deficiencies: (i) some variables that confound actions are not observed, and (ii)…

Machine Learning · Computer Science 2023-03-21 Siyu Chen , Yitan Wang , Zhaoran Wang , Zhuoran Yang

Off-policy evaluation (OPE) in both contextual bandits and reinforcement learning allows one to evaluate novel decision policies without needing to conduct exploration, which is often costly or otherwise infeasible. The problem's importance…

Machine Learning · Computer Science 2019-06-11 Nathan Kallus , Masatoshi Uehara

Off-policy estimation for long-horizon problems is important in many real-life applications such as healthcare and robotics, where high-fidelity simulators may not be available and on-policy evaluation is expensive or impossible. Recently,…

Machine Learning · Computer Science 2020-03-26 Ali Mousavi , Lihong Li , Qiang Liu , Denny Zhou

High-quality data plays a central role in ensuring the accuracy of policy evaluation. This paper initiates the study of efficient and safe data collection for bandit policy evaluation. We formulate the problem and investigate its several…

Machine Learning · Computer Science 2022-06-22 Runzhe Wan , Branislav Kveton , Rui Song

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