English
Related papers

Related papers: On The Statistical Complexity of Offline Decision-…

200 papers

A central problem in online learning and decision making -- from bandits to reinforcement learning -- is to understand what modeling assumptions lead to sample-efficient learning guarantees. We consider a general adversarial decision making…

Machine Learning · Computer Science 2022-06-28 Dylan J. Foster , Alexander Rakhlin , Ayush Sekhari , Karthik Sridharan

This paper considers a class of real-time decision making problems to minimize the expected value of a function that depends on a random variable $\xi$ under an unknown distribution $\mathbb{P}$. In this process, samples of $\xi$ are…

Optimization and Control · Mathematics 2020-09-08 Dan Li , Sonia Martinez

Goal-oriented Reinforcement Learning, where the agent needs to reach the goal state while simultaneously minimizing the cost, has received significant attention in real-world applications. Its theoretical formulation, stochastic shortest…

Machine Learning · Computer Science 2022-06-13 Ming Yin , Wenjing Chen , Mengdi Wang , Yu-Xiang Wang

This paper presents an axiomatic approach to finite Markov decision processes where the discount rate is zero. One of the principal difficulties in the no discounting case is that, even if attention is restricted to stationary policies, a…

Optimization and Control · Mathematics 2022-11-23 Adam Jonsson

The classical algorithms for online learning and decision-making have the benefit of achieving the optimal performance guarantees, but suffer from computational complexity limitations when implemented at scale. More recent sophisticated…

Machine Learning · Computer Science 2022-10-19 Guanghui Wang , Zihao Hu , Vidya Muthukumar , Jacob Abernethy

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 study off-policy evaluation and learning from sequential data in a structured class of Markov decision processes that arise from repeated interactions with an exogenous sequence of arrivals with contexts, which generate unknown…

Machine Learning · Computer Science 2021-10-20 Nathan Kallus , Angela Zhou

We propose a new approach to competitive analysis in online scheduling by introducing the novel concept of competitive-ratio approximation schemes. Such a scheme algorithmically constructs an online algorithm with a competitive ratio…

Data Structures and Algorithms · Computer Science 2012-11-01 Elisabeth Günther , Olaf Maurer , Nicole Megow , Andreas Wiese

We study online capacitated resource allocation, a natural generalization of online stochastic max-weight bipartite matching. This problem is motivated by ride-sharing and Internet advertising applications, where online arrivals may have…

Data Structures and Algorithms · Computer Science 2024-06-13 Alexander Braun , Thomas Kesselheim , Tristan Pollner , Amin Saberi

Offline reinforcement learning, which seeks to utilize offline/historical data to optimize sequential decision-making strategies, has gained surging prominence in recent studies. Due to the advantage that appropriate function approximators…

Machine Learning · Computer Science 2022-03-14 Ming Yin , Yaqi Duan , Mengdi Wang , Yu-Xiang Wang

Traditional online learning models are typically initialized from scratch. By contrast, contemporary real-world applications often have access to historical datasets that can potentially enhanced the online learning processes. We study how…

Machine Learning · Computer Science 2025-12-19 Wang Chi Cheung , Lixing Lyu

We consider the problem of sequentially making decisions that are rewarded by "successes" and "failures" which can be predicted through an unknown relationship that depends on a partially controllable vector of attributes for each instance.…

Machine Learning · Statistics 2017-09-18 Yingfei Wang , Chu Wang , Warren Powell

This paper studies the statistical theory of batch data reinforcement learning with function approximation. Consider the off-policy evaluation problem, which is to estimate the cumulative value of a new target policy from logged history…

Machine Learning · Computer Science 2020-02-25 Yaqi Duan , Mengdi Wang

Much of modern learning theory has been split between two regimes: the classical offline setting, where data arrive independently, and the online setting, where data arrive adversarially. While the former model is often both computationally…

Machine Learning · Statistics 2022-06-01 Adam Block , Yuval Dagan , Noah Golowich , Alexander Rakhlin

We study the efficient off-policy evaluation of natural stochastic policies, which are defined in terms of deviations from the behavior policy. This is a departure from the literature on off-policy evaluation where most work consider the…

Machine Learning · Computer Science 2020-11-05 Nathan Kallus , Masatoshi Uehara

We study online optimization problems in which the cost function depends on latent, time-varying parameters that are unmeasurable and governed by unknown dynamics. Specifically, we consider a strongly convex cost function whose linear term…

Optimization and Control · Mathematics 2026-05-22 Shivanshu Tripathi , Maziar Raissi

This paper investigates off-policy evaluation in contextual bandits, aiming to quantify the performance of a target policy using data collected under a different and potentially unknown behavior policy. Recently, methods based on conformal…

Machine Learning · Statistics 2025-07-23 Yilong Wan , Yuqiang Li , Xianyi Wu

Offline contextual bandits allow one to learn policies from historical/offline data without requiring online interaction. However, offline policy optimization that maximizes overall expected rewards can unintentionally amplify the reward…

Machine Learning · Computer Science 2026-01-07 Yihong Guo , Junjie Luo , Guodong Gao , Ritu Agarwal , Anqi Liu

We study the problem of online learning with dynamics, where a learner interacts with a stateful environment over multiple rounds. In each round of the interaction, the learner selects a policy to deploy and incurs a cost that depends on…

Machine Learning · Computer Science 2020-12-04 Kush Bhatia , Karthik Sridharan

This thesis aims to study some of the mathematical challenges that arise in the analysis of statistical sequential decision-making algorithms for postoperative patients follow-up. Stochastic bandits (multiarmed, contextual) model the…

Machine Learning · Statistics 2024-05-06 Patrick Saux