English
Related papers

Related papers: PAC-Bayesian Offline Contextual Bandits With Guara…

200 papers

We derive a novel PAC-Bayesian generalization bound for reinforcement learning that explicitly accounts for Markov dependencies in the data, through the chain's mixing time. This contributes to overcoming challenges in obtaining…

Machine Learning · Computer Science 2026-02-10 Abdelkrim Zitouni , Mehdi Hennequin , Juba Agoun , Ryan Horache , Nadia Kabachi , Omar Rivasplata

We apply the PAC-Bayes theory to the setting of learning-to-optimize. To the best of our knowledge, we present the first framework to learn optimization algorithms with provable generalization guarantees (PAC-bounds) and explicit trade-off…

Machine Learning · Computer Science 2023-02-16 Michael Sucker , Peter Ochs

Most bandit policies are designed to either minimize regret in any problem instance, making very few assumptions about the underlying environment, or in a Bayesian sense, assuming a prior distribution over environment parameters. The former…

Machine Learning · Computer Science 2021-01-07 Branislav Kveton , Martin Mladenov , Chih-Wei Hsu , Manzil Zaheer , Csaba Szepesvari , Craig Boutilier

Exploration policies in Bayesian bandits maximize the average reward over problem instances drawn from some distribution $\mathcal{P}$. In this work, we learn such policies for an unknown distribution $\mathcal{P}$ using samples from…

Machine Learning · Computer Science 2020-06-11 Craig Boutilier , Chih-Wei Hsu , Branislav Kveton , Martin Mladenov , Csaba Szepesvari , Manzil Zaheer

We address the problem of learning in an online, bandit setting where the learner must repeatedly select among $K$ actions, but only receives partial feedback based on its choices. We establish two new facts: First, using a new algorithm…

Machine Learning · Computer Science 2011-10-28 Alina Beygelzimer , John Langford , Lihong Li , Lev Reyzin , Robert E. Schapire

Preference-based feedback is important for many applications where direct evaluation of a reward function is not feasible. A notable recent example arises in reinforcement learning from human feedback on large language models. For many of…

Machine Learning · Computer Science 2023-07-24 Viraj Mehta , Ojash Neopane , Vikramjeet Das , Sen Lin , Jeff Schneider , Willie Neiswanger

We present and prove properties of a new offline policy evaluator for an exploration learning setting which is superior to previous evaluators. In particular, it simultaneously and correctly incorporates techniques from importance…

Machine Learning · Computer Science 2012-10-19 Miroslav Dudik , Dumitru Erhan , John Langford , Lihong Li

Contextual bandit algorithms are sensitive to the estimation method of the outcome model as well as the exploration method used, particularly in the presence of rich heterogeneity or complex outcome models, which can lead to difficult…

Machine Learning · Computer Science 2018-12-18 Maria Dimakopoulou , Zhengyuan Zhou , Susan Athey , Guido Imbens

Most off-policy evaluation methods for contextual bandits have focused on the expected outcome of a policy, which is estimated via methods that at best provide only asymptotic guarantees. However, in many applications, the expectation may…

Machine Learning · Statistics 2022-10-27 Muhammad Faaiz Taufiq , Jean-Francois Ton , Rob Cornish , Yee Whye Teh , Arnaud Doucet

Automated decision-making algorithms drive applications such as recommendation systems and search engines. These algorithms often rely on off-policy contextual bandits or off-policy learning (OPL). Conventionally, OPL selects actions that…

We present a new algorithm for the contextual bandit learning problem, where the learner repeatedly takes one of $K$ actions in response to the observed context, and observes the reward only for that chosen action. Our method assumes access…

Machine Learning · Computer Science 2014-10-15 Alekh Agarwal , Daniel Hsu , Satyen Kale , John Langford , Lihong Li , Robert E. Schapire

We study the off-policy evaluation problem---estimating the value of a target policy using data collected by another policy---under the contextual bandit model. We consider the general (agnostic) setting without access to a consistent model…

Machine Learning · Statistics 2017-11-15 Yu-Xiang Wang , Alekh Agarwal , Miroslav Dudik

Control policies from imitation learning can often fail to generalize to novel environments due to imperfect demonstrations or the inability of imitation learning algorithms to accurately infer the expert's policies. In this paper, we…

Robotics · Computer Science 2020-12-04 Allen Z. Ren , Sushant Veer , Anirudha Majumdar

In the stochastic contextual bandit setting, regret-minimizing algorithms have been extensively researched, but their instance-minimizing best-arm identification counterparts remain seldom studied. In this work, we focus on the stochastic…

Machine Learning · Statistics 2023-10-04 Zhaoqi Li , Lillian Ratliff , Houssam Nassif , Kevin Jamieson , Lalit Jain

We introduce the cram method as a general statistical framework for evaluating the final learned policy from a multi-armed contextual bandit algorithm, using the dataset generated by the same bandit algorithm. The proposed on-policy…

Machine Learning · Computer Science 2025-04-16 Zeyang Jia , Kosuke Imai , Michael Lingzhi Li

A fundamental challenge in contextual bandits is to develop flexible, general-purpose algorithms with computational requirements no worse than classical supervised learning tasks such as classification and regression. Algorithms based on…

Machine Learning · Computer Science 2020-06-24 Dylan J. Foster , Alexander Rakhlin

We propose the first boosting algorithm for off-policy learning from logged bandit feedback. Unlike existing boosting methods for supervised learning, our algorithm directly optimizes an estimate of the policy's expected reward. We analyze…

Machine Learning · Computer Science 2023-05-03 Ben London , Levi Lu , Ted Sandler , Thorsten Joachims

We study risk-aware offline policy learning, aiming to learn a decision rule from logged data that is optimal under general risk criteria. This problem is crucial in high-stakes domains where online interaction is infeasible and adverse…

Machine Learning · Statistics 2026-05-18 Yilong Wan , Yuqiang Li , Xianyi Wu

Our goal is to learn control policies for robots that provably generalize well to novel environments given a dataset of example environments. The key technical idea behind our approach is to leverage tools from generalization theory in…

Robotics · Computer Science 2020-08-27 Anirudha Majumdar , Alec Farid , Anoopkumar Sonar

We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic policies in contextual bandits with continuous action spaces. Our work is motivated by practical scenarios where the target policy needs to be…

Machine Learning · Computer Science 2022-12-29 Haanvid Lee , Jongmin Lee , Yunseon Choi , Wonseok Jeon , Byung-Jun Lee , Yung-Kyun Noh , Kee-Eung Kim