中文
相关论文

相关论文: Thompson Sampling Achieves $\tilde O(\sqrt{T})$ Re…

200 篇论文

We present safe control of partially-observed linear time-varying systems in the presence of unknown and unpredictable process and measurement noise. We introduce a control algorithm that minimizes dynamic regret, i.e., that minimizes the…

系统与控制 · 电气工程与系统科学 2023-04-03 Hongyu Zhou , Vasileios Tzoumas

This article presents a dynamic regret analysis for stochastic model predictive control (SMPC) in linear systems with quadratic performance index and additive and multiplicative uncertainties. Under a finite support assumption, the problem…

最优化与控制 · 数学 2025-02-04 Sungho Shin , Sen Na , Mihai Anitescu

Much of the recent literature on bandit learning focuses on algorithms that aim to converge on an optimal action. One shortcoming is that this orientation does not account for time sensitivity, which can play a crucial role when learning an…

机器学习 · 计算机科学 2020-01-09 Daniel Russo , Benjamin Van Roy

We study the control of an \emph{unknown} linear dynamical system under general convex costs. The objective is minimizing regret vs. the class of disturbance-feedback-controllers, which encompasses all stabilizing…

机器学习 · 计算机科学 2020-10-30 Orestis Plevrakis , Elad Hazan

We consider the problem of learning in Linear Quadratic Control systems whose transition parameters are initially unknown. Recent results in this setting have demonstrated efficient learning algorithms with regret growing with the square…

机器学习 · 计算机科学 2020-07-03 Asaf Cassel , Alon Cohen , Tomer Koren

We provide an approach for the analysis of randomised exploration algorithms like Thompson sampling that does not rely on forced optimism or posterior inflation. With this, we demonstrate that in the $d$-dimensional linear bandit setting,…

机器学习 · 计算机科学 2025-02-14 Marc Abeille , David Janz , Ciara Pike-Burke

We study the problem of online multi-task learning where the tasks are performed within similar but not necessarily identical multi-armed bandit environments. In particular, we study how a learner can improve its overall performance across…

机器学习 · 计算机科学 2022-06-20 Zhi Wang , Chicheng Zhang , Kamalika Chaudhuri

We propose ${\tt AdaTS}$, a Thompson sampling algorithm that adapts sequentially to bandit tasks that it interacts with. The key idea in ${\tt AdaTS}$ is to adapt to an unknown task prior distribution by maintaining a distribution over its…

机器学习 · 计算机科学 2022-02-28 Soumya Basu , Branislav Kveton , Manzil Zaheer , Csaba Szepesvári

We introduce a sampling-based learning method for solving optimal control problems involving task satisfaction constraints for systems with partially known dynamics. The control problems are defined by a cost to be minimized and a task to…

系统与控制 · 电气工程与系统科学 2020-04-14 Peter Varnai , Dimos V. Dimarogonas

In the stochastic multi-armed bandit problem, a randomized probability matching policy called Thompson sampling (TS) has shown excellent performance in various reward models. In addition to the empirical performance, TS has been shown to…

机器学习 · 计算机科学 2023-02-06 Jongyeong Lee , Junya Honda , Chao-Kai Chiang , Masashi Sugiyama

Thompson sampling (TS) has optimal regret and excellent empirical performance in multi-armed bandit problems. Yet, in Bayesian optimization, TS underperforms popular acquisition functions (e.g., EI, UCB). TS samples arms according to the…

机器学习 · 统计学 2024-12-02 David Sweet

In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve almost the same regret as the optimal non-private…

机器学习 · 计算机科学 2022-07-08 Osama A. Hanna , Antonious M. Girgis , Christina Fragouli , Suhas Diggavi

Practitioners conducting adaptive experiments often encounter two competing priorities: maximizing total welfare (or `reward') through effective treatment assignment and swiftly concluding experiments to implement population-wide…

机器学习 · 计算机科学 2024-07-31 Chao Qin , Daniel Russo

Thompson Sampling provides an efficient technique to introduce prior knowledge in the multi-armed bandit problem, along with providing remarkable empirical performance. In this paper, we revisit the Thompson Sampling algorithm under rewards…

机器学习 · 计算机科学 2019-12-09 Abhimanyu Dubey , Alex Pentland

This paper investigates the problem of regret minimization in linear time-varying (LTV) dynamical systems. Due to the simultaneous presence of uncertainty and non-stationarity, designing online control algorithms for unknown LTV systems…

机器学习 · 计算机科学 2022-06-07 Yuzhen Han , Ruben Solozabal , Jing Dong , Xingyu Zhou , Martin Takac , Bin Gu

In this work, we focus on the design of optimal controllers that must comply with an information structure. State-of-the-art approaches do so based on the H2 or Hinfty norm to minimize the expected or worst-case cost in the presence of…

系统与控制 · 电气工程与系统科学 2025-11-24 Daniele Martinelli , Andrea Martin , Giancarlo Ferrari-Trecate , Luca Furieri

The problem of regret minimization for online adaptive control of linear-quadratic systems is studied. In this problem, the true system transition parameters (matrices $A$ and $B$) are unknown, and the objective is to design and analyze…

最优化与控制 · 数学 2022-10-31 Mohammad Akbari , Bahman Gharesifard , Tamas Linder

In this paper, the tracking control problem of an Euler-Lagrange system is addressed with regard to parametric uncertainties, and an adaptive-robust control strategy, christened Time-Delayed Adaptive Robust Control (TARC), is presented.…

系统与控制 · 计算机科学 2018-05-10 Spandan Roy , Indra Narayan Kar , Jinoh Lee , Nikos Tsagarakis , Darwin G. Caldwell

Thompson sampling (TS) is one of the most popular exploration techniques in reinforcement learning (RL). However, most TS algorithms with theoretical guarantees are difficult to implement and not generalizable to Deep RL. While the emerging…

机器学习 · 计算机科学 2024-06-19 Haque Ishfaq , Yixin Tan , Yu Yang , Qingfeng Lan , Jianfeng Lu , A. Rupam Mahmood , Doina Precup , Pan Xu

We address the problem of stochastic combinatorial semi-bandits, where a player selects among P actions from the power set of a set containing d base items. Adaptivity to the problem's structure is essential in order to obtain optimal…

机器学习 · 计算机科学 2024-11-18 Julien Zhou , Pierre Gaillard , Thibaud Rahier , Houssam Zenati , Julyan Arbel