中文
相关论文

相关论文: Global Convergence of Policy Gradient Primal-dual …

200 篇论文

Policy optimization (PO) is a key ingredient for reinforcement learning (RL). For control design, certain constraints are usually enforced on the policies to optimize, accounting for either the stability, robustness, or safety concerns on…

最优化与控制 · 数学 2021-02-16 Kaiqing Zhang , Bin Hu , Tamer Başar

In safety-critical applications, reinforcement learning (RL) needs to consider safety constraints. However, theoretical understandings of constrained RL for continuous control are largely absent. As a case study, this paper presents a…

最优化与控制 · 数学 2024-06-07 Feiran Zhao , Keyou You

We explore reinforcement learning methods for finding the optimal policy in the linear quadratic regulator (LQR) problem. In particular, we consider the convergence of policy gradient methods in the setting of known and unknown parameters.…

机器学习 · 计算机科学 2021-06-25 Ben Hambly , Renyuan Xu , Huining Yang

Direct policy gradient methods for reinforcement learning and continuous control problems are a popular approach for a variety of reasons: 1) they are easy to implement without explicit knowledge of the underlying model 2) they are an…

机器学习 · 计算机科学 2019-03-26 Maryam Fazel , Rong Ge , Sham M. Kakade , Mehran Mesbahi

Policy optimization (PO), an essential approach of reinforcement learning for a broad range of system classes, requires significantly more system data than indirect (identification-followed-by-control) methods or behavioral-based direct…

最优化与控制 · 数学 2023-09-18 Feiran Zhao , Florian Dörfler , Keyou You

Risk-aware control, though with promise to tackle unexpected events, requires a known exact dynamical model. In this work, we propose a model-free framework to learn a risk-aware controller with a focus on the linear system. We formulate it…

系统与控制 · 电气工程与系统科学 2021-06-01 Feiran Zhao , Keyou You

Recent advances in constrained reinforcement learning (RL) have endowed reinforcement learning with certain safety guarantees. However, deploying existing constrained RL algorithms in continuous control tasks with general hard constraints…

机器学习 · 计算机科学 2023-12-22 Shutong Ding , Jingya Wang , Yali Du , Ye Shi

This paper proposes and analyzes two new policy learning methods: regularized policy gradient (RPG) and iterative policy optimization (IPO), for a class of discounted linear-quadratic control (LQC) problems over an infinite time horizon…

最优化与控制 · 数学 2025-10-08 Xin Guo , Xinyu Li , Renyuan Xu

Policy gradient methods are a powerful family of reinforcement learning algorithms for continuous control that optimize a policy directly. However, standard first-order methods often converge slowly. Second-order methods can accelerate…

系统与控制 · 电气工程与系统科学 2025-11-05 Amirreza Valaei , Arash Bahari Kordabad , Sadegh Soudjani

The problem of constrained reinforcement learning (CRL) holds significant importance as it provides a framework for addressing critical safety satisfaction concerns in the field of reinforcement learning (RL). However, with the introduction…

机器学习 · 计算机科学 2023-05-24 Chengbin Xuan , Feng Zhang , Faliang Yin , Hak-Keung Lam

Safe Reinforcement Learning (RL) often faces significant issues such as constraint violations and instability, necessitating the use of constrained policy optimization, which seeks optimal policies while ensuring adherence to specific…

机器学习 · 计算机科学 2025-08-07 Ning Yang , Pengyu Wang , Guoqing Liu , Haifeng Zhang , Pin Lv , Jun Wang

Gradient-based methods have been widely used for system design and optimization in diverse application domains. Recently, there has been a renewed interest in studying theoretical properties of these methods in the context of control and…

最优化与控制 · 数学 2022-10-11 Bin Hu , Kaiqing Zhang , Na Li , Mehran Mesbahi , Maryam Fazel , Tamer Başar

We study the problem of computing an optimal policy of an infinite-horizon discounted constrained Markov decision process (constrained MDP). Despite the popularity of Lagrangian-based policy search methods used in practice, the oscillation…

最优化与控制 · 数学 2024-01-18 Dongsheng Ding , Chen-Yu Wei , Kaiqing Zhang , Alejandro Ribeiro

We consider policy gradient algorithms for the indefinite least squares stationary optimal control, e.g., linear-quadratic-regulator (LQR) with indefinite state and input penalization matrices. Such a setup has important applications in…

最优化与控制 · 数学 2020-02-13 Jingjing Bu , Mehran Mesbahi

With the outstanding performance of policy gradient (PG) method in the reinforcement learning field, the convergence theory of it has aroused more and more interest recently. Meanwhile, the significant importance and abundant theoretical…

最优化与控制 · 数学 2024-04-19 Xinpei Zhang , Guangyan Jia

This paper studies an infinite horizon optimal control problem for discrete-time linear system and quadratic criteria, both with random parameters which are independent and identically distributed with respect to time. In this general…

最优化与控制 · 数学 2024-03-04 Deyue Li

Nonlinear control systems with partial information to the decision maker are prevalent in a variety of applications. As a step toward studying such nonlinear systems, this work explores reinforcement learning methods for finding the optimal…

机器学习 · 计算机科学 2025-04-11 Yinbin Han , Meisam Razaviyayn , Renyuan Xu

We consider solutions to the linear quadratic Gaussian (LQG) regulator problem via policy gradient (PG) methods. Although PG methods have demonstrated strong theoretical guarantees in solving the linear quadratic regulator (LQR) problem,…

最优化与控制 · 数学 2025-07-15 Kasra Fallah , Leonardo F. Toso , James Anderson

Constrained optimization is popularly seen in reinforcement learning for addressing complex control tasks. From the perspective of dynamic system, iteratively solving a constrained optimization problem can be framed as the temporal…

机器学习 · 计算机科学 2025-01-28 Tianqi Zhang , Puzhen Yuan , Guojian Zhan , Ziyu Lin , Yao Lyu , Zhenzhi Qin , Jingliang Duan , Liping Zhang , Shengbo Eben Li

Reinforcement Learning (RL) has emerged as a powerful framework for sequential decision-making in dynamic environments, particularly when system parameters are unknown. This paper investigates RL-based control for entropy-regularized…

系统与控制 · 电气工程与系统科学 2025-12-02 Gabriel Diaz , Lucky Li , Wenhao Zhang
‹ 上一页 1 2 3 10 下一页 ›