中文
相关论文

相关论文: Policy iteration for discrete-time systems with di…

200 篇论文

We develop a general approach to the Policy Improvement Algorithm (PIA) for stochastic control problems for continuous-time processes. The main results assume only that the controls lie in a compact metric space and give general sufficient…

概率论 · 数学 2015-10-01 Saul D. Jacka , Aleksandar Mijatović

We present differentiable predictive control (DPC), a method for learning constrained neural control policies for linear systems with probabilistic performance guarantees. We employ automatic differentiation to obtain direct policy…

系统与控制 · 电气工程与系统科学 2022-01-28 Jan Drgona , Aaron Tuor , Draguna Vrabie

The PI control of first-order linear passive systems through a delayed communication channel is revisited in light of the relative stability concept called sigma-stability. Treating the delayed communication channel as a transport PDE, the…

最优化与控制 · 数学 2019-11-14 Fernando Castaños , Edgar Estrada , Sabine Mondié , Adrián Ramírez

When transferring a control policy from simulation to a physical system, the policy needs to be robust to variations in the dynamics to perform well. Commonly, the optimal policy overfits to the approximate model and the corresponding…

机器学习 · 计算机科学 2021-05-27 Michael Lutter , Shie Mannor , Jan Peters , Dieter Fox , Animesh Garg

The problem of synthesizing stochastic explicit model predictive control policies is known to be quickly intractable even for systems of modest complexity when using classical control-theoretic methods. To address this challenge, we present…

机器学习 · 计算机科学 2022-05-24 Ján Drgoňa , Sayak Mukherjee , Aaron Tuor , Mahantesh Halappanavar , Draguna Vrabie

Linear consensus iterations guarantee asymptotic convergence, thereby, limiting their applicability in applications where consensus value needs to be used in real time to perform a system level task. It also leads to wastage of power and…

最优化与控制 · 数学 2017-06-22 Mangal Prakash , Saurav Talukdar , Sandeep Attree , Vikas Yadav , Murti Salapaka

In this paper, we consider the finite-state approximation of a discrete-time constrained Markov decision process (MDP) under the discounted and average cost criteria. Using the linear programming formulation of the constrained discounted…

最优化与控制 · 数学 2018-07-10 Naci Saldi

This paper discusses the in-domain feedback stabilization of reaction-diffusion PDEs with Robin boundary conditions in the presence of an uncertain time- and spatially-varying delay in the distributed actuation. The proposed control design…

最优化与控制 · 数学 2021-08-18 Hugo Lhachemi , Christophe Prieur , Robert Shorten

This paper studies the problem of event-triggered impulsive control for discrete-time systems. A novel periodic event-triggering scheme with two tunable parameters is presented to determine the moments of updating impulsive control signals…

最优化与控制 · 数学 2023-04-28 Kexue Zhang , Elena Braverman

This study investigates computationally efficient algorithms for solving discrete-time infinite-horizon single-agent/multi-agent dynamic models with continuous actions. It shows that we can easily reduce the computational costs by slightly…

综合经济学 · 经济学 2025-02-21 Takeshi Fukasawa

This paper discusses the robustness of the constant-delay predictor feedback in the case of an uncertain time-varying input delay. Specifically, we study the stability of the closed-loop system when the predictor feedback is designed based…

最优化与控制 · 数学 2019-08-29 Hugo Lhachemi , Christophe Prieur , Robert Shorten

We study the synthesis of a policy in a Markov decision process (MDP) following which an agent reaches a target state in the MDP while minimizing its total discounted cost. The problem combines a reachability criterion with a discounted…

最优化与控制 · 数学 2021-03-18 Yagiz Savas , Christos K. Verginis , Michael Hibbard , Ufuk Topcu

Dynamic decisions are pivotal to economic policy making. We show how existing evidence from randomized control trials can be utilized to guide personalized decisions in challenging dynamic environments with budget and capacity constraints.…

计量经济学 · 经济学 2024-11-26 Karun Adusumilli , Friedrich Geiecke , Claudio Schilter

A static non-linear homogeneous feedback for a fixed-time stabilization of a linear time-invariant (LTI) system is designed in such a way that the settling time is assigned exactly to a prescribed constant for all nonzero initial…

系统与控制 · 电气工程与系统科学 2023-07-06 Andrey Polyakov , Miroslav Krstic

This paper develops a quantized Q-learning algorithm for the optimal control of controlled diffusion processes on $\mathbb{R}^d$ under both discounted and ergodic (average) cost criteria. We first establish near-optimality of finite-state…

最优化与控制 · 数学 2026-03-16 Erhan Bayraktar , Ali D. Kara , Somnath Pradhan , Serdar Yuksel

In this paper, we study the control properties of a new class of stochastic ensemble systems that consists of families of random variables. These random variables provide an increasingly good approximation of an unknown discrete,…

系统与控制 · 电气工程与系统科学 2023-04-25 Nirabhra Mandal , Mohammad Khajenejad , Sonia Martinez

In this paper, we propose a class of discrete-time approximation schemes for stochastic optimal control problems under the $G$-expectation framework. The proposed schemes are constructed recursively based on piecewise constant policy. We…

最优化与控制 · 数学 2021-10-05 Lianzi Jiang

We present a method for the steady state optimization of nonlinear delay differential equations. The method ensures stability and robustness, where a system is called robust if it remains stable despite uncertain parameters. Essentially, we…

最优化与控制 · 数学 2019-03-14 Jonas Otten , Martin Mönnigmann

Constrained decision-making is essential for designing safe policies in real-world control systems, yet simulated environments often fail to capture real-world adversities. We consider the problem of learning a policy that will maximize the…

机器学习 · 计算机科学 2026-02-10 Sourav Ganguly , Kishan Panaganti , Arnob Ghosh , Adam Wierman

Tackling large approximate dynamic programming or reinforcement learning problems requires methods that can exploit regularities, or intrinsic structure, of the problem in hand. Most current methods are geared towards exploiting the…

机器学习 · 计算机科学 2014-07-03 Amir-massoud Farahmand , Doina Precup , André M. S. Barreto , Mohammad Ghavamzadeh