中文
相关论文

相关论文: Dynamic Regret for Strongly Adaptive Methods and O…

200 篇论文

We study online reinforcement learning in linear Markov decision processes with adversarial losses and bandit feedback, without prior knowledge on transitions or access to simulators. We introduce two algorithms that achieve improved regret…

机器学习 · 计算机科学 2023-10-19 Haolin Liu , Chen-Yu Wei , Julian Zimmert

In this paper, we study dynamic regret in unconstrained online convex optimization (OCO) with movement costs. Specifically, we generalize the standard setting by allowing the movement cost coefficients $\lambda_t$ to vary arbitrarily over…

机器学习 · 计算机科学 2026-02-09 Emmanuel Esposito , Andrew Jacobsen , Hao Qiu , Mengxiao Zhang

In the online non-stochastic control problem, an agent sequentially selects control inputs for a linear dynamical system when facing unknown and adversarially selected convex costs and disturbances. A common metric for evaluating control…

最优化与控制 · 数学 2025-04-24 Vijeth Hebbar , Cédric Langbort

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

We consider distributed online convex optimization problems, where the distributed system consists of various computing units connected through a time-varying communication graph. In each time step, each computing unit selects a constrained…

机器学习 · 计算机科学 2019-12-23 Deming Yuan , Alexandre Proutiere , Guodong Shi

We present an algorithm guaranteeing dynamic regret bounds for online omniprediction with long term constraints. The goal in this recently introduced problem is for a learner to generate a sequence of predictions which are broadcast to a…

机器学习 · 计算机科学 2025-10-09 Yahav Bechavod , Jiuyao Lu , Aaron Roth

In this paper, we broaden the horizon of online convex optimization (OCO), and consider multi-objective OCO, where there are $K$ distinct loss function sequences, and an algorithm has to choose its action at time $t$, before the $K$ loss…

机器学习 · 计算机科学 2026-02-11 Rahul Vaze , Sumiran Mishra

In online convex optimization it is well known that certain subclasses of objective functions are much easier than arbitrary convex functions. We are interested in designing adaptive methods that can automatically get fast rates in as many…

机器学习 · 计算机科学 2021-08-31 Tim van Erven , Wouter M. Koolen

We consider adaptive control of the Linear Quadratic Regulator (LQR), where an unknown linear system is controlled subject to quadratic costs. Leveraging recent developments in the estimation of linear systems and in robust controller…

机器学习 · 计算机科学 2018-05-25 Sarah Dean , Horia Mania , Nikolai Matni , Benjamin Recht , Stephen Tu

We study the regret guarantee for risk-sensitive reinforcement learning (RSRL) via distributional reinforcement learning (DRL) methods. In particular, we consider finite episodic Markov decision processes whose objective is the entropic…

机器学习 · 计算机科学 2024-01-26 Hao Liang , Zhi-Quan Luo

We consider online learning in episodic loop-free Markov decision processes (MDPs), where the loss function can change arbitrarily between episodes, and the transition function is not known to the learner. We show…

机器学习 · 计算机科学 2019-05-21 Aviv Rosenberg , Yishay Mansour

We study the Stochastic Shortest Path (SSP) problem with a linear mixture transition kernel, where an agent repeatedly interacts with a stochastic environment and seeks to reach certain goal state while minimizing the cumulative cost.…

机器学习 · 计算机科学 2024-02-15 Qiwei Di , Jiafan He , Dongruo Zhou , Quanquan Gu

We consider the framework of non-stationary stochastic optimization [Besbes et al, 2015] with squared error losses and noisy gradient feedback where the dynamic regret of an online learner against a time varying comparator sequence is…

机器学习 · 计算机科学 2020-10-02 Dheeraj Baby , Yu-Xiang Wang

We consider an online learning process to forecast a sequence of outcomes for nonconvex models. A typical measure to evaluate online learning algorithms is regret but such standard definition of regret is intractable for nonconvex models…

机器学习 · 计算机科学 2018-11-30 Sergul Aydore , Lee Dicker , Dean Foster

This paper addresses Online Convex Optimization (OCO) problems where the constraints have additive perturbations that (i) vary over time and (ii) are not known at the time to make a decision. Perturbations may not be i.i.d. generated and…

最优化与控制 · 数学 2019-06-04 Víctor Valls , George Iosifidis , Douglas J. Leith , Leandros Tassiulas

We study the problem of non-stationary dueling bandits and provide the first adaptive dynamic regret algorithm for this problem. The only two existing attempts in this line of work fall short across multiple dimensions, including…

机器学习 · 计算机科学 2022-10-27 Thomas Kleine Buening , Aadirupa Saha

To efficiently solve online problems with complicated constraints, projection-free algorithms including online frank-wolfe (OFW) and its variants have received significant interest recently. However, in the general case, existing efficient…

机器学习 · 计算机科学 2024-06-25 Yuanyu Wan , Lijun Zhang

We consider the online control problem with an unknown linear dynamical system in the presence of adversarial perturbations and adversarial convex loss functions. Although the problem is widely studied in model-based control, it remains…

系统与控制 · 电气工程与系统科学 2024-03-12 Zishun Liu , Yongxin Chen

Deep reinforcement learning has achieved impressive successes yet often requires a very large amount of interaction data. This result is perhaps unsurprising, as using complicated function approximation often requires more data to fit, and…

机器学习 · 计算机科学 2020-11-20 Jonathan N. Lee , Aldo Pacchiano , Vidya Muthukumar , Weihao Kong , Emma Brunskill

We study Online Convex Optimization with adversarial constraints (COCO). At each round a learner selects an action from a convex decision set and then an adversary reveals a convex cost and a convex constraint function. The goal of the…

机器学习 · 计算机科学 2025-11-17 Abhishek Sinha , Rahul Vaze