English
Related papers

Related papers: Regret-Optimal Control for Finite-State Systems

200 papers

In this paper, we investigate a worst-case-scenario control problem with a partially observed state. We consider a non-stochastic formulation, where noises and disturbances in our dynamics are uncertain variables which take values in finite…

Optimization and Control · Mathematics 2022-12-14 Aditya Dave , Nishanth Venkatesh , Andreas A. Malikopoulos

Robust optimal or min-max model predictive control (MPC) approaches aim to guarantee constraint satisfaction over a known, bounded uncertainty set while minimizing a worst-case performance bound. Traditionally, these methods compute a…

Systems and Control · Electrical Eng. & Systems 2025-09-04 J. Wehbeh , E. C. Kerrigan

We consider the problem of nonstochastic control with a sequence of quadratic losses, i.e., LQR control. We provide an efficient online algorithm that achieves an optimal dynamic (policy) regret of $\tilde{O}(\text{max}\{n^{1/3}…

Machine Learning · Computer Science 2022-06-22 Dheeraj Baby , Yu-Xiang Wang

This paper is concerned with mismatched disturbance rejection control for the second-order discrete-time systems.Different from previous work, the controllability of the system is applied to design the disturbance compensation gain, which…

Optimization and Control · Mathematics 2022-05-04 Shichao Lv , Kai Peng , Hongxia Wang , Huanshui Zhang

The online meta-learning framework has arisen as a powerful tool for the continual lifelong learning setting. The goal for an agent is to quickly learn new tasks by drawing on prior experience, while it faces with tasks one after another.…

Machine Learning · Computer Science 2021-09-30 Parvin Nazari , Esmaile Khorram

System level synthesis enables improved robust MPC formulations by allowing for joint optimization of the nominal trajectory and controller. This paper introduces a tailored algorithm for solving the corresponding disturbance feedback…

Optimization and Control · Mathematics 2024-09-05 Antoine P. Leeman , Johannes Köhler , Florian Messerer , Amon Lahr , Moritz Diehl , Melanie N. Zeilinger

We consider the problem of designing policies for partially observable Markov decision processes (POMDPs) with dynamic coherent risk objectives. Synthesizing risk-averse optimal policies for POMDPs requires infinite memory and thus…

Robotics · Computer Science 2019-09-30 Mohamadreza Ahmadi , Masahiro Ono , Michel D. Ingham , Richard M. Murray , Aaron D. Ames

We consider undiscounted reinforcement learning in Markov decision processes (MDPs) where both the reward functions and the state-transition probabilities may vary (gradually or abruptly) over time. For this problem setting, we propose an…

Machine Learning · Computer Science 2019-09-11 Pratik Gajane , Ronald Ortner , Peter Auer

Controllers for dynamical systems that operate in safety-critical settings must account for stochastic disturbances. Such disturbances are often modeled as process noise in a dynamical system, and common assumptions are that the underlying…

Systems and Control · Electrical Eng. & Systems 2023-01-24 Thom Badings , Licio Romao , Alessandro Abate , David Parker , Hasan A. Poonawala , Marielle Stoelinga , Nils Jansen

Control systems are inevitably affected by external disturbances, and a major objective of the control design is to attenuate or eliminate their adverse effects on the system performance. This paper presents a disturbance rejection approach…

Systems and Control · Electrical Eng. & Systems 2020-07-30 Zhitao Li , Amin Vahidi-Moghaddam , Hamidreza Modares , Jinsheng Sun

We consider robust control synthesis for linear systems with complex specifications that are affected by uncertain disturbances. This work is motivated by autonomous systems interacting with partially known, time-varying environments. Given…

Optimization and Control · Mathematics 2018-08-27 Damian Frick , Tony A. Wood , Gian Ulli , Maryam Kamgarpour

This paper considers a collection of networked nonlinear dynamical systems, and addresses the synthesis of feedback controllers that seek optimal operating points corresponding to the solution of network-wide constrained optimization…

Optimization and Control · Mathematics 2015-04-03 Emiliano Dall'Anese , Sairaj Dhople , Georgios B. Giannakis

This paper addresses the problem of designing a data-driven feedback controller for complex nonlinear dynamical systems in the presence of time-varying disturbances with unknown dynamics. Such disturbances are modeled as the "unknown" part…

Systems and Control · Electrical Eng. & Systems 2023-11-22 Niyousha Rahimi , Mehran Mesbahi

The growing prevalence of drift and shocks in modern decision environments exposes a gap between classical optimization theory and real-world practice. Standard models assume fixed objectives, yet organizations from hospitals to power grids…

Computational Finance · Quantitative Finance 2025-09-18 JINHO CHA

We introduce robustness in \textit{restless multi-armed bandits} (RMABs), a popular model for constrained resource allocation among independent stochastic processes (arms). Nearly all RMAB techniques assume stochastic dynamics are precisely…

Machine Learning · Computer Science 2022-06-23 Jackson A. Killian , Lily Xu , Arpita Biswas , Milind Tambe

We study, to our knowledge, the first tractable multistage ex-ante distributionally robust regret optimization (DRRO) formulation for stochastic control. We consider finite-horizon LQR under common stage-law ambiguity: disturbances are…

Optimization and Control · Mathematics 2026-04-08 Lukas-Benedikt Fiechtner , Jose Blanchet

We study the problem of online learning in predictive control of an unknown linear dynamical system with time varying cost functions which are unknown apriori. Specifically, we study the online learning problem where the control algorithm…

Machine Learning · Computer Science 2022-11-01 Deepan Muthirayan , Jianjun Yuan , Dileep Kalathil , Pramod P. Khargonekar

We present a variety of projection-based linear regression algorithms with a focus on modern machine-learning models and their algorithmic performance. We study the role of the relaxation parameter in generalized Kaczmarz algorithms and…

Machine Learning · Statistics 2025-11-12 Halyun Jeong , Palle E. T. Jorgensen , Hyun-Kyoung Kwon , Myung-Sin Song

Deadbeat Robust Model Predictive Control (DRMPC) is introduced as a new approach of Robust Model Predictive Control (RMPC) for linear systems with additive disturbances. Its main idea is to completely extinguish the effect of the…

Optimization and Control · Mathematics 2025-10-02 G. Schildbach

In this paper we consider stochastic multiarmed bandit problems. Recently a policy, DMED, is proposed and proved to achieve the asymptotic bound for the model that each reward distribution is supported in a known bounded interval, e.g.…

Statistics Theory · Mathematics 2012-02-20 Junya Honda , Akimichi Takemura