中文
相关论文

相关论文: Minimal regret state estimation of time-varying sy…

200 篇论文

We consider the classic problem of online convex optimisation. Whereas the notion of static regret is relevant for stationary problems, the notion of switching regret is more appropriate for non-stationary problems. A switching regret is…

机器学习 · 计算机科学 2025-03-07 Stephen Pasteris , Chris Hicks , Vasilios Mavroudis , Mark Herbster

This paper is concerned with the problem of state estimation for discrete-time linear systems in the presence of additional (equality or inequality) constraints on the state (or estimate). By use of the minimum variance duality, the…

最优化与控制 · 数学 2021-12-08 Prabhat K. Mishra , Girish Chowdhary , Prashant G. Mehta

Regret minimization is a powerful tool for solving large-scale extensive-form games. State-of-the-art methods rely on minimizing regret locally at each decision point. In this work we derive a new framework for regret minimization on…

计算机科学与博弈论 · 计算机科学 2018-09-11 Gabriele Farina , Christian Kroer , Tuomas Sandholm

We study the problem of minimizing polarization and disagreement in the Friedkin-Johnsen opinion dynamics model under incomplete information. Unlike prior work that assumes a static setting with full knowledge of agents' innate opinions, we…

机器学习 · 计算机科学 2026-03-09 Federico Cinus , Yuko Kuroki , Atsushi Miyauchi , Francesco Bonchi

This work presents a scalable control framework based on nonlinear Model Predictive Control for high-dimensional dynamical systems. The proposed approach addresses the key challenges of model scalability and partial observability by…

流体动力学 · 物理学 2025-11-25 Luigi Marra , Onofrio Semeraro , Lionel Mathelin , Andrea Meilán-Vila , Stefano Discetti

The setting of an agent making decisions under uncertainty and under dynamic constraints is common for the fields of optimal control, reinforcement learning, and recently also for online learning. In the online learning setting, the quality…

系统与控制 · 电气工程与系统科学 2023-04-18 Aren Karapetyan , Anastasios Tsiamis , Efe C. Balta , Andrea Iannelli , John Lygeros

The paper provides a new approach to the determination of a single state value for stochastic output feedback problems using paradigms from Model Predictive Control, particularly the distinction between open-loop and closed-loop control and…

最优化与控制 · 数学 2023-03-03 Mohammad S. Ramadan , Robert R. Bitmead , Ke Huang

Traditional statements of the celebrated Kalman filter algorithm focus on the estimation of state, but not the output. For any outputs, measured or auxiliary, it is usually assumed that the posterior state estimates and known inputs are…

最优化与控制 · 数学 2016-10-26 Ameet S. Deshpande

Regret minimization is treated as the golden rule in the traditional study of online learning. However, regret minimization algorithms tend to converge to the static optimum, thus being suboptimal for changing environments. To address this…

机器学习 · 计算机科学 2020-02-07 Lijun Zhang , Shiyin Lu , Tianbao Yang

State estimation incorporates the feedback in optimization based advanced process control systems and is very important for the performance of model predictive control. We describe the extended Kalman filter, the unscented Kalman filter,…

We present an optimistic Q-learning algorithm for regret minimization in average reward reinforcement learning under an additional assumption on the underlying MDP that for all policies, the time to visit some frequent state $s_0$ is finite…

机器学习 · 计算机科学 2025-06-17 Priyank Agrawal , Shipra Agrawal

A large variety of real-world Reinforcement Learning (RL) tasks is characterized by a complex and heterogeneous structure that makes end-to-end (or flat) approaches hardly applicable or even infeasible. Hierarchical Reinforcement Learning…

机器学习 · 计算机科学 2023-05-12 Gianluca Drappo , Alberto Maria Metelli , Marcello Restelli

Satellite dynamics and tracking remain important challenges in the context of space exploration and communication systems. Accurate state estimation is essential to maintain reliable orbital motion and system performance. This paper…

系统与控制 · 电气工程与系统科学 2026-04-16 Moh Kamalul Wafi

We consider the problem of controlling an unknown linear dynamical system under adversarially changing convex costs and full feedback of both the state and cost function. We present the first computationally-efficient algorithm that attains…

机器学习 · 计算机科学 2022-06-06 Asaf Cassel , Alon Cohen , Tomer Koren

Optimising queries in real-world situations under imperfect conditions is still a problem that has not been fully solved. We consider finding the optimal order in which to execute a given set of selection operators under partial ignorance…

数据库 · 计算机科学 2015-07-30 Khaled H. Alyoubi , Sven Helmer , Peter T. Wood

We study the linear bandit problem that accounts for partially observable features. Without proper handling, unobserved features can lead to linear regret in the decision horizon $T$, as their influence on rewards is unknown. To tackle this…

机器学习 · 统计学 2025-08-19 Wonyoung Kim , Sungwoo Park , Garud Iyengar , Assaf Zeevi , Min-hwan Oh

The increasing availability of sensing techniques provides a great opportunity for engineers to design state estimation methods, which are optimal for the system under observation and the observed noise patterns. However, these patterns…

系统与控制 · 电气工程与系统科学 2023-06-19 Jean-Sébastien Brouillon , Florian Dörfler , Giancarlo Ferrari-Trecate

This paper develops a robust extended Kalman filter to estimate the rotor angles and the rotor speeds of synchronous generators of a multimachine power system. Using a batch-mode regression form, the filter processes together predicted…

系统与控制 · 电气工程与系统科学 2021-04-06 Marcos Netto , Junbo Zhao , Lamine Mili

We investigate the problem of continuous-time causal estimation under a minimax criterion. Let $X^T = \{X_t,0\leq t\leq T\}$ be governed by the probability law $P_{\theta}$ from a class of possible laws indexed by $\theta \in \Lambda$, and…

信息论 · 计算机科学 2014-07-09 Albert No , Tsachy Weissman

We present a stochastic predictive controller for discrete time linear time invariant systems under incomplete state information. Our approach is based on a suitable choice of control policies, stability constraints, and employment of a…

最优化与控制 · 数学 2018-02-27 Prabhat Kumar Mishra , Debasish Chatterjee , Daniel E. Quevedo