English
Related papers

Related papers: Functional Natural Policy Gradients

200 papers

A fundamental question for companies with large amount of logged data is: How to use such logged data together with incoming streaming data to make good decisions? Many companies currently make decisions via online A/B tests, but wrong…

Machine Learning · Computer Science 2020-11-10 Li Ye , Yishi Lin , Hong Xie , John C. S. Lui

In the random-order model for online learning, the sequence of losses is chosen upfront by an adversary and presented to the learner after a random permutation. Any random-order input is \emph{asymptotically} equivalent to a stochastic…

Machine Learning · Computer Science 2025-10-06 Martino Bernasconi , Andrea Celli , Riccardo Colini-Baldeschi , Federico Fusco , Stefano Leonardi , Matteo Russo

We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem. We study this question both in the setting of prediction with expert advice, and for more general combinatorial decision…

Machine Learning · Computer Science 2015-03-02 Wouter M. Koolen , Tim van Erven

We consider model selection in stochastic bandit and reinforcement learning problems. Given a set of base learning algorithms, an effective model selection strategy adapts to the best learning algorithm in an online fashion. We show that by…

Machine Learning · Computer Science 2020-06-11 Yasin Abbasi-Yadkori , Aldo Pacchiano , My Phan

In online learning, the data is provided in a sequential order, and the goal of the learner is to make online decisions to minimize overall regrets. This note is concerned with continuous-time models and algorithms for several online…

Machine Learning · Statistics 2024-05-20 Lexing Ying

Off-policy learning is a framework for optimizing policies without deploying them, using data collected by another policy. In recommender systems, this is especially challenging due to the imbalance in logged data: some items are…

Machine Learning · Computer Science 2024-10-23 Matej Cief , Branislav Kveton , Michal Kompan

Policy Optimization (PO) is a widely used approach to address continuous control tasks. In this paper, we introduce the notion of mediator feedback that frames PO as an online learning problem over the policy space. The additional available…

Machine Learning · Computer Science 2020-12-16 Alberto Maria Metelli , Matteo Papini , Pierluca D'Oro , Marcello Restelli

Sequential prediction problems such as imitation learning, where future observations depend on previous predictions (actions), violate the common i.i.d. assumptions made in statistical learning. This leads to poor performance in theory and…

Machine Learning · Computer Science 2015-03-17 Stephane Ross , Geoffrey J. Gordon , J. Andrew Bagnell

We study a new class of online learning problems where each of the online algorithm's actions is assigned an adversarial value, and the loss of the algorithm at each step is a known and deterministic function of the values assigned to its…

Machine Learning · Computer Science 2014-05-20 Ofer Dekel , Jian Ding , Tomer Koren , Yuval Peres

We consider the problem of online learning where the sequence of actions played by the learner must adhere to an unknown safety constraint at every round. The goal is to minimize regret with respect to the best safe action in hindsight…

Machine Learning · Computer Science 2024-03-08 Karthik Sridharan , Seung Won Wilson Yoo

We consider the problem of learning to optimize an unknown Markov decision process (MDP). We show that, if the MDP can be parameterized within some known function class, we can obtain regret bounds that scale with the dimensionality, rather…

Machine Learning · Statistics 2014-11-04 Ian Osband , Benjamin Van Roy

We study a generalization of the problem of online learning in adversarial linear contextual bandits by incorporating loss functions that belong to a reproducing kernel Hilbert space, which allows for a more flexible modeling of complex…

Machine Learning · Statistics 2023-10-04 Gergely Neu , Julia Olkhovskaya , Sattar Vakili

We study the problem of incentive-compatible online learning with bandit feedback. In this class of problems, the experts are self-interested agents who might misrepresent their preferences with the goal of being selected most often. The…

Machine Learning · Computer Science 2024-05-13 Julian Zimmert , Teodor V. Marinov

In this work we provide provable regret guarantees for an online meta-learning control algorithm in an iterative control setting, where in each iteration the system to be controlled is a linear deterministic system that is different and…

Machine Learning · Computer Science 2022-02-07 Deepan Muthirayan , Pramod Khargonekar

We study offline-online reinforcement learning in linear mixture Markov decision processes (MDPs) under environment shift. In the offline phase, data are collected by an unknown behavior policy and may come from a mismatched environment,…

Machine Learning · Computer Science 2026-04-15 Zhongjun Zhang , Sean R. Sinclair

Optimization models used to make discrete decisions often contain uncertain parameters that are context-dependent and estimated through prediction. To account for the quality of the decision made based on the prediction, decision-focused…

Machine Learning · Computer Science 2024-07-30 Noah Schutte , Krzysztof Postek , Neil Yorke-Smith

We tackle the problem of Non-stochastic Control (NSC) with the aim of obtaining algorithms whose policy regret is proportional to the difficulty of the controlled environment. Namely, we tailor the Follow The Regularized Leader (FTRL)…

Optimization and Control · Mathematics 2024-04-24 Naram Mhaisen , George Iosifidis

Policy regret is a well established notion of measuring the performance of an online learning algorithm against an adaptive adversary. We study restrictions on the adversary that enable efficient minimization of the \emph{complete policy…

Machine Learning · Statistics 2022-04-26 Dhruv Malik , Yuanzhi Li , Aarti Singh

This paper describes a new parameter-free online learning algorithm for changing environments. In comparing against algorithms with the same time complexity as ours, we obtain a strongly adaptive regret bound that is a factor of at least…

Machine Learning · Statistics 2017-08-08 Kwang-Sung Jun , Francesco Orabona , Rebecca Willett , Stephen Wright

This paper investigates regret minimization, statistical inference, and their interplay in high-dimensional online decision-making based on the sparse linear context bandit model. We integrate the $\varepsilon$-greedy bandit algorithm for…

Machine Learning · Computer Science 2025-05-20 Congyuan Duan , Wanteng Ma , Jiashuo Jiang , Dong Xia