English
Related papers

Related papers: Optimization Landscape of Policy Gradient Methods …

200 papers

Markov Decision Processes are classically solved using Value Iteration and Policy Iteration algorithms. Recent interest in Reinforcement Learning has motivated the study of methods inspired by optimization, such as gradient ascent. Among…

Machine Learning · Computer Science 2021-05-05 Sajad Khodadadian , Prakirt Raj Jhunjhunwala , Sushil Mahavir Varma , Siva Theja Maguluri

This paper introduces a method for efficiently updating a nominal stabilizing static output feedback (SOF) controller in perturbed linear systems. As operating points and state-space matrices change in dynamic systems, accommodating updates…

Systems and Control · Electrical Eng. & Systems 2025-12-03 MirSaleh Bahavarnia , Ahmad F. Taha

Policy gradient methods are a vital ingredient behind the success of modern reinforcement learning. Modern policy gradient methods, although successful, introduce a residual error in gradient estimation. In this work, we argue that this…

Machine Learning · Computer Science 2024-03-05 Pulkit Katdare , Anant Joshi , Katherine Driggs-Campbell

Gradient matching with Gaussian processes is a promising tool for learning parameters of ordinary differential equations (ODE's). The essence of gradient matching is to model the prior over state variables as a Gaussian process which…

Machine Learning · Statistics 2016-10-25 Nico S. Gorbach , Stefan Bauer , Joachim M. Buhmann

In deep learning, stochastic gradient descent (SGD) and its momentum-based variants are widely used for optimization. However, the internal dynamics of these methods remain underexplored. In this paper, we analyze gradient behavior through…

Machine Learning · Computer Science 2025-03-11 Zhipeng Yao , Rui Yu , Guisong Chang , Ying Li , Yu Zhang , Dazhou Li

Policy gradient (PG) gives rise to a rich class of reinforcement learning (RL) methods. Recently, there has been an emerging trend to accelerate the existing PG methods such as REINFORCE by the \emph{variance reduction} techniques. However,…

Machine Learning · Computer Science 2021-05-31 Junyu Zhang , Chengzhuo Ni , Zheng Yu , Csaba Szepesvari , Mengdi Wang

We propose in this paper a new minimization algorithm based on a slightly modified version of the scalar auxiliary variable (SAV) approach coupled with a relaxation step and an adaptive strategy. It enjoys several distinct advantages over…

Numerical Analysis · Mathematics 2023-05-11 Xinyu Liu , Jie Shen , Xiaongxiong Zhang

Policy gradient algorithms are widely used in reinforcement learning and belong to the class of approximate dynamic programming methods. This paper studies two key policy gradient algorithms, the Natural Policy Gradient and the Gauss-Newton…

Systems and Control · Electrical Eng. & Systems 2026-05-11 Bowen Song , Sebastien Gros , Andrea Iannelli

Model-free reinforcement learning attempts to find an optimal control action for an unknown dynamical system by directly searching over the parameter space of controllers. The convergence behavior and statistical properties of these…

Optimization and Control · Mathematics 2021-03-17 Hesameddin Mohammadi , Armin Zare , Mahdi Soltanolkotabi , Mihailo R. Jovanović

This paper develops and analyzes feedback-based online optimization methods to regulate the output of a linear time-invariant (LTI) dynamical system to the optimal solution of a time-varying convex optimization problem. The design of the…

Optimization and Control · Mathematics 2018-05-31 Marcello Colombino , Emiliano Dall'Anese , Andrey Bernstein

Stochastic distributed optimization methods that solve an optimization problem over a multi-agent network have played an important role in a variety of large-scale signal processing and machine leaning applications. Among the existing…

Optimization and Control · Mathematics 2023-02-06 Songyang Ge , Tsung-Hui Chang

The stochastic gradient descent (SGD) method is a widely used approach for solving stochastic optimization problems, but its convergence is typically slow. Existing variance reduction techniques, such as SAGA, improve convergence by…

Optimization and Control · Mathematics 2025-11-21 Fabio Nobile , Matteo Raviola , Nathan Schaeffer

We study state-feedback design for continuous-time LTI systems with a control input and an external input-output pair. Our objective is to determine feedback gains that render the closed-loop system (strictly) passive with respect to the…

Optimization and Control · Mathematics 2026-05-07 Armin Gießler , Pol Jané-Soneira , Sören Hohmann

Policy gradient methods are an attractive approach to multi-agent reinforcement learning problems due to their convergence properties and robustness in partially observable scenarios. However, there is a significant performance gap between…

Machine Learning · Computer Science 2021-05-07 Bozhidar Vasilev , Tarun Gupta , Bei Peng , Shimon Whiteson

Consider a discrete-time Linear Quadratic Regulator (LQR) problem solved using policy gradient descent when the system matrices are unknown. The gradient is transmitted across a noisy channel over a finite time horizon using analog…

Optimization and Control · Mathematics 2025-07-22 Ashwin Verma , Aritra Mitra , Lintao Ye , Vijay Gupta

We present a model-based globally convergent policy gradient method (PGM) for linear quadratic Gaussian (LQG) control. Firstly, we establish equivalence between optimizing dynamic output feedback controllers and designing a static feedback…

Optimization and Control · Mathematics 2024-02-27 Tomonori Sadamoto , Fumiya Nakamata

We develop policy gradients methods for stochastic control with exit time in a model-free setting. We propose two types of algorithms for learning either directly the optimal policy or by learning alternately the value function (critic) and…

Computational Finance · Quantitative Finance 2023-02-16 Mohamed Hamdouche , Pierre Henry-Labordere , Huyen Pham

Projected policy gradient under the simplex parameterization, policy gradient and natural policy gradient under the softmax parameterization, are fundamental algorithms in reinforcement learning. There have been a flurry of recent…

Optimization and Control · Mathematics 2024-04-12 Jiacai Liu , Wenye Li , Ke Wei

This paper presents a discrete-time passivity-based analysis of the gradient descent method for a class of functions with sector-bounded gradients. Using a loop transformation, it is shown that the gradient descent method can be interpreted…

Optimization and Control · Mathematics 2024-11-26 Sepehr Moalemi , James Richard Forbes

We consider the problem of designing a feedback controller which robustly regulates an LTI system to an optimal operating point in the presence of unmeasured disturbances. A general design framework based on so-called optimality models was…

Optimization and Control · Mathematics 2022-08-18 John W. Simpson-Porco