English
Related papers

Related papers: Some remarks on gradient dominance and LQR policy …

200 papers

Policy gradient methods, where one searches for the policy of interest by maximizing the value functions using first-order information, become increasingly popular for sequential decision making in reinforcement learning, games, and…

Optimization and Control · Mathematics 2023-10-10 Shicong Cen , Yuejie Chi

Constrained Reinforcement Learning (CRL) tackles sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints, which are often formulated as…

Machine Learning · Computer Science 2024-11-13 Alessandro Montenegro , Marco Mussi , Matteo Papini , Alberto Maria Metelli

Due to its applications in many different places in machine learning and other connected engineering applications, the problem of minimization of a smooth function that satisfies the Polyak-{\L}ojasiewicz condition receives much attention…

Optimization and Control · Mathematics 2022-12-09 Ilya A. Kuruzov , Fedor S. Stonyakin , Mohammad S. Alkousa

Most prior work on the convergence of gradient descent (GD) for overparameterized neural networks relies on strong assumptions on the step size (infinitesimal), the hidden-layer width (infinite), or the initialization (large, spectral,…

Machine Learning · Computer Science 2025-05-20 Ziqing Xu , Hancheng Min , Salma Tarmoun , Enrique Mallada , Rene Vidal

We study the problem of efficiently estimating policies that simultaneously optimize multiple objectives in reinforcement learning (RL). Given $n$ objectives (or tasks), we seek the optimal partition of these objectives into $k \ll n$…

Machine Learning · Computer Science 2026-02-24 Zhenshuo Zhang , Minxuan Duan , Youran Ye , Hongyang R. Zhang

For continuing environments, reinforcement learning (RL) methods commonly maximize the discounted reward criterion with discount factor close to 1 in order to approximate the average reward (the gain). However, such a criterion only…

Machine Learning · Computer Science 2022-07-05 Vektor Dewanto , Marcus Gallagher

In this paper, we consider the problem of learning safe policies for probabilistic-constrained reinforcement learning (RL). Specifically, a safe policy or controller is one that, with high probability, maintains the trajectory of the agent…

Machine Learning · Computer Science 2024-03-14 Weiqin Chen , Dharmashankar Subramanian , Santiago Paternain

In order to model risk aversion in reinforcement learning, an emerging line of research adapts familiar algorithms to optimize coherent risk functionals, a class that includes conditional value-at-risk (CVaR). Because optimizing the…

Machine Learning · Computer Science 2021-03-09 Audrey Huang , Liu Leqi , Zachary C. Lipton , Kamyar Azizzadenesheli

From the perspective of control theory, the gradient descent optimization methods can be regarded as a dynamic system where various control techniques can be designed to enhance the performance of the optimization method. In this paper, we…

Optimization and Control · Mathematics 2025-03-19 Osama F. Abdel Aal , Necdet Sinan Ozbek , Jairo Viola , YangQuan Chen

Motivated by the growing use of artificial intelligence (AI) tools in control design, this paper analyses the intersection between results from gradient methods for the model-free linear quadratic regulator (LQR), and linear feedforward…

Systems and Control · Electrical Eng. & Systems 2025-05-27 Arthur Castello B. de Oliveira , Milad Siami , Eduardo D. Sontag

Distributed training and increasing the gradient update frequency are practical strategies to accelerate learning and improve performance, but both exacerbate a central challenge: \textit{policy lag}, which is the mismatch between the…

This paper deals with distributed policy optimization in reinforcement learning, which involves a central controller and a group of learners. In particular, two typical settings encountered in several applications are considered:…

Machine Learning · Computer Science 2021-04-21 Tianyi Chen , Kaiqing Zhang , Georgios B. Giannakis , Tamer Başar

The linear quadratic regulator (LQR) problem has reemerged as an important theoretical benchmark for reinforcement learning-based control of complex dynamical systems with continuous state and action spaces. In contrast with nearly all…

Machine Learning · Computer Science 2020-05-04 Benjamin Gravell , Peyman Mohajerin Esfahani , Tyler Summers

When applying imitation learning techniques to fit a policy from expert demonstrations, one can take advantage of prior stability/robustness assumptions on the expert's policy and incorporate such control-theoretic prior knowledge…

Optimization and Control · Mathematics 2021-03-25 Aaron Havens , Bin Hu

This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns. Due…

Multiagent Systems · Computer Science 2022-12-06 Xiaoxiao Zhao , Jinlong Lei , Li Li , Jie Chen

This paper focuses on the online gradient and proximal-gradient methods with stochastic gradient errors. In particular, we examine the performance of the online gradient descent method when the cost satisfies the Polyak-\L ojasiewicz (PL)…

Optimization and Control · Mathematics 2024-07-16 Seunghyun Kim , Liam Madden , Emiliano Dall'Anese

When training neural networks with low-precision computation, rounding errors often cause stagnation or are detrimental to the convergence of the optimizers; in this paper we study the influence of rounding errors on the convergence of the…

Machine Learning · Statistics 2025-01-22 Lu Xia , Michiel E. Hochstenbach , Stefano Massei

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple…

Optimization and Control · Mathematics 2023-10-09 Quan Xiao , Songtao Lu , Tianyi Chen

Policy gradient is a generic and flexible reinforcement learning approach that generally enjoys simplicity in analysis, implementation, and deployment. In the last few decades, this approach has been extensively advanced for fully…

Machine Learning · Computer Science 2020-05-26 Kamyar Azizzadenesheli , Yisong Yue , Animashree Anandkumar

Policy gradient (PG) methods have played an essential role in the empirical successes of reinforcement learning. In order to handle large state-action spaces, PG methods are typically used with function approximation. In this setting, the…