中文
相关论文

相关论文: Exploration by Optimization with Hybrid Regularize…

200 篇论文

This study considers the partial monitoring problem with $k$-actions and $d$-outcomes and provides the first best-of-both-worlds algorithms, whose regrets are favorably bounded both in the stochastic and adversarial regimes. In particular,…

机器学习 · 计算机科学 2022-10-11 Taira Tsuchiya , Shinji Ito , Junya Honda

We study the multi-armed bandit problem with adversarially chosen delays in the Best-of-Both-Worlds (BoBW) framework, which aims to achieve near-optimal performance in both stochastic and adversarial environments. While prior work has made…

机器学习 · 计算机科学 2025-10-21 Ofir Schlisselberg , Tal Lancewicki , Peter Auer , Yishay Mansour

Bandit Convex Optimization (BCO) is a fundamental framework for modeling sequential decision-making with partial information, where the only feedback available to the player is the one-point or two-point function values. In this paper, we…

机器学习 · 计算机科学 2020-07-07 Peng Zhao , Guanghui Wang , Lijun Zhang , Zhi-Hua Zhou

We develop the first general semi-bandit algorithm that simultaneously achieves $\mathcal{O}(\log T)$ regret for stochastic environments and $\mathcal{O}(\sqrt{T})$ regret for adversarial environments without knowledge of the regime or the…

机器学习 · 计算机科学 2019-09-27 Julian Zimmert , Haipeng Luo , Chen-Yu Wei

We study the problem of determining an effective exploration strategy in static and non-linear optimization problems, which depend on an unknown scalar parameter to be learned from online collected noisy data. An optimal trade-off between…

最优化与控制 · 数学 2024-09-13 Ying Wang , Mirko Pasquini , Kévin Colin , Håkan Hjalmarsson

This study considers online learning with general directed feedback graphs. For this problem, we present best-of-both-worlds algorithms that achieve nearly tight regret bounds for adversarial environments as well as poly-logarithmic regret…

机器学习 · 计算机科学 2022-12-29 Shinji Ito , Taira Tsuchiya , Junya Honda

We provide a simple and efficient algorithm for adversarial $k$-action $d$-outcome non-degenerate locally observable partial monitoring game for which the $n$-round minimax regret is bounded by $6(d+1) k^{3/2} \sqrt{n \log(k)}$, matching…

机器学习 · 计算机科学 2019-10-28 Tor Lattimore , Csaba Szepesvari

Partial monitoring is a general model for sequential learning with limited feedback formalized as a game between two players. In this game, the learner chooses an action and at the same time the opponent chooses an outcome, then the learner…

机器学习 · 统计学 2015-10-01 Junpei Komiyama , Junya Honda , Hiroshi Nakagawa

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…

机器学习 · 计算机科学 2020-12-16 Alberto Maria Metelli , Matteo Papini , Pierluca D'Oro , Marcello Restelli

We study Online Convex Optimization (OCO) with adversarial constraints, where an online algorithm must make sequential decisions to minimize both convex loss functions and cumulative constraint violations. We focus on a setting where the…

机器学习 · 统计学 2025-03-14 Jordan Lekeufack , Michael I. Jordan

We study online learning problems in which a decision maker has to take a sequence of decisions subject to $m$ long-term constraints. The goal of the decision maker is to maximize their total reward, while at the same time achieving small…

机器学习 · 计算机科学 2022-09-16 Matteo Castiglioni , Andrea Celli , Alberto Marchesi , Giulia Romano , Nicola Gatti

Constrained Online Convex Optimization (COCO) can be seen as a generalization of the standard Online Convex Optimization (OCO) framework. At each round, a cost function and constraint function are revealed after a learner chooses an action.…

机器学习 · 计算机科学 2025-05-30 Ricardo N. Ferreira , Cláudia Soares

This paper considers the multi-armed bandit (MAB) problem and provides a new best-of-both-worlds (BOBW) algorithm that works nearly optimally in both stochastic and adversarial settings. In stochastic settings, some existing BOBW algorithms…

机器学习 · 计算机科学 2022-06-15 Shinji Ito , Taira Tsuchiya , Junya Honda

We study online learning in finite-horizon episodic Markov decision processes (MDPs) under the challenging aggregate bandit feedback model, where the learner observes only the cumulative loss incurred in each episode, rather than individual…

机器学习 · 计算机科学 2025-10-28 Shinji Ito , Kevin Jamieson , Haipeng Luo , Arnab Maiti , Taira Tsuchiya

Motivated by alternating learning dynamics in two-player games, a recent work by Cevher et al.(2024) shows that $o(\sqrt{T})$ alternating regret is possible for any $T$-round adversarial Online Linear Optimization (OLO) problem, and left as…

机器学习 · 计算机科学 2025-06-19 Soumita Hait , Ping Li , Haipeng Luo , Mengxiao Zhang

We present a new anytime algorithm that achieves near-optimal regret for any instance of finite stochastic partial monitoring. In particular, the new algorithm achieves the minimax regret, within logarithmic factors, for both "easy" and…

机器学习 · 计算机科学 2012-07-03 Gabor Bartok , Navid Zolghadr , Csaba Szepesvari

In contrast to the classic formulation of partial monitoring, linear partial monitoring can model infinite outcome spaces, while imposing a linear structure on both the losses and the observations. This setting can be viewed as a…

机器学习 · 计算机科学 2026-01-15 Federico Di Gennaro , Khaled Eldowa , Nicolò Cesa-Bianchi

We consider a generalization of the celebrated Online Convex Optimization (OCO) framework with adversarial online constraints. In this problem, an online learner interacts with an adversary sequentially over multiple rounds. At the…

机器学习 · 计算机科学 2026-01-07 Subhamon Supantha , Abhishek Sinha

Online bilevel optimization (OBO) has emerged as a powerful framework for many machine learning problems. Prior works have developed several algorithms that minimize the standard bilevel local regret or the window-averaged bilevel local…

机器学习 · 计算机科学 2026-05-12 Tingkai Jia , Haiguang Wang , Cheng Chen

Recent literature has made much progress in understanding \emph{online LQR}: a modern learning-theoretic take on the classical control problem in which a learner attempts to optimally control an unknown linear dynamical system with fully…

机器学习 · 计算机科学 2020-10-06 Max Simchowitz
‹ 上一页 1 2 3 10 下一页 ›