English
Related papers

Related papers: Online Learning with Costly Features in Non-statio…

200 papers

Motivated by applications to online advertising and recommender systems, we consider a game-theoretic model with delayed rewards and asynchronous, payoff-based feedback. In contrast to previous work on delayed multi-armed bandits, we focus…

Computer Science and Game Theory · Computer Science 2020-06-22 Amélie Héliou , Panayotis Mertikopoulos , Zhengyuan Zhou

Determining what experience to generate to best facilitate learning (i.e. exploration) is one of the distinguishing features and open challenges in reinforcement learning. The advent of distributed agents that interact with parallel…

Machine Learning · Computer Science 2019-12-17 Tom Schaul , Diana Borsa , David Ding , David Szepesvari , Georg Ostrovski , Will Dabney , Simon Osindero

Much of the current work on reinforcement learning studies episodic settings, where the agent is reset between trials to an initial state distribution, often with well-shaped reward functions. Non-episodic settings, where the agent must…

Machine Learning · Computer Science 2020-06-23 John D. Co-Reyes , Suvansh Sanjeev , Glen Berseth , Abhishek Gupta , Sergey Levine

By reusing data throughout training, off-policy deep reinforcement learning algorithms offer improved sample efficiency relative to on-policy approaches. For continuous action spaces, the most popular methods for off-policy learning include…

Machine Learning · Computer Science 2023-12-01 Jared Markowitz , Jesse Silverberg , Gary Collins

In digital health and EdTech, recommendation systems face a significant challenge: users often choose impulsively, in ways that conflict with the platform's long-term payoffs. This misalignment makes it difficult to effectively learn to…

Machine Learning · Computer Science 2024-02-22 Arpit Agarwal , Rad Niazadeh , Prathamesh Patil

Making an informed decision -- for example, when choosing a career or housing -- requires knowledge about the available options. Such knowledge is generally acquired through costly trial and error, but this learning process can be disrupted…

Machine Learning · Computer Science 2022-04-15 Sarah H. Cen , Devavrat Shah

This paper studies bandit problems where an agent has access to offline data that might be utilized to potentially improve the estimation of each arm's reward distribution. A major obstacle in this setting is the existence of compound…

Machine Learning · Computer Science 2023-12-21 Wen Huang , Xintao Wu

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

Most modern systems strive to learn from interactions with users, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information. We initiate a study of the interplay between exploration and…

Computer Science and Game Theory · Computer Science 2017-11-21 Yishay Mansour , Aleksandrs Slivkins , Zhiwei Steven Wu

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

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

Selective labels are a common feature of consequential decision-making applications, referring to the lack of observed outcomes under one of the possible decisions. This paper reports work in progress on learning decision policies in the…

Machine Learning · Computer Science 2020-11-04 Dennis Wei

In the problem of online learning for changing environments, data are sequentially received one after another over time, and their distribution assumptions may vary frequently. Although existing methods demonstrate the effectiveness of…

Machine Learning · Computer Science 2023-07-18 Chen Zhao , Feng Mi , Xintao Wu , Kai Jiang , Latifur Khan , Christan Grant , Feng Chen

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

We consider the problem of learning to choose actions using contextual information when provided with limited feedback in the form of relative pairwise comparisons. We study this problem in the dueling-bandits framework of Yue et al.…

Machine Learning · Computer Science 2015-06-16 Miroslav Dudík , Katja Hofmann , Robert E. Schapire , Aleksandrs Slivkins , Masrour Zoghi

Today's online advertisers procure digital ad impressions through interacting with autobidding platforms: advertisers convey high level procurement goals via setting levers such as budget, target return-on-investment, max cost per click,…

Information Retrieval · Computer Science 2023-07-13 Jason Cheuk Nam Liang , Haihao Lu , Baoyu Zhou

We study online learning problems in which a decision maker has to make a sequence of costly decisions, with the goal of maximizing their expected reward while adhering to budget and return-on-investment (ROI) constraints. Existing…

Computer Science and Game Theory · Computer Science 2024-03-05 Matteo Castiglioni , Andrea Celli , Christian Kroer

We study the problem of federated stochastic multi-arm contextual bandits with unknown contexts, in which M agents are faced with different bandits and collaborate to learn. The communication model consists of a central server and the…

Machine Learning · Computer Science 2024-01-31 Jiabin Lin , Shana Moothedath

This paper identifies and addresses dynamic selection problems in online learning algorithms with endogenous data. In a contextual multi-armed bandit model, a novel bias (self-fulfilling bias) arises because the endogeneity of the data…

Econometrics · Economics 2023-09-29 Jin Li , Ye Luo , Xiaowei Zhang

In order for an e-commerce platform to maximize its revenue, it must recommend customers items they are most likely to purchase. However, the company often has business constraints on these items, such as the number of each item in stock.…

Optimization and Control · Mathematics 2019-11-19 Andrea Boskovic , Qinyi Chen , Dominik Kufel , Zijie Zhou