English
Related papers

Related papers: Global linear convergence of entropy-regularized s…

200 papers

This work revisits standard policy gradient methods used on restricted policy classes, which are known to get stuck in suboptimal critical points. We identify an important cause for this phenomenon to be that the policy gradient is itself…

Machine Learning · Computer Science 2026-05-12 Alex DeWeese , Guannan Qu

We develop a generic policy gradient method with the global optimality guarantee for robust Markov Decision Processes (MDPs). While policy gradient methods are widely used for solving dynamic decision problems due to their scalable and…

Machine Learning · Computer Science 2024-11-01 Qiuhao Wang , Shaohang Xu , Chin Pang Ho , Marek Petrik

Many control problems in environments that can be modeled as Markov decision processes (MDPs) concern infinite-time horizon specifications. The classical aim in this context is to compute a control policy that maximizes the probability of…

Systems and Control · Computer Science 2017-05-03 Ruediger Ehlers , Salar Moarref , Ufuk Topcu

We study decentralized multiagent optimization over networks, modeled as undirected graphs. The optimization problem consists of minimizing a nonconvex smooth function plus a convex extended-value function, which enforces constraints or…

Optimization and Control · Mathematics 2024-12-13 Xiaokai Chen , Tianyu Cao , Gesualdo Scutari

The convergence of deterministic policy gradient under the Hadamard parameterization is studied in the tabular setting and the linear convergence of the algorithm is established. To this end, we first show that the error decreases at an…

Optimization and Control · Mathematics 2023-11-28 Jiacai Liu , Jinchi Chen , Ke Wei

Markov Decision Processes (MDPs) have been used to formulate many decision-making problems in science and engineering. The objective is to synthesize the best decision (action selection) policies to maximize expected rewards (minimize…

Optimization and Control · Mathematics 2015-07-08 Mahmoud El Chamie , Behcet Acikmese

We consider optimization problems in which the goal is find a $k$-dimensional subspace of $\mathbb{R}^n$, $k<<n$, which minimizes a convex and smooth loss. Such problems generalize the fundamental task of principal component analysis (PCA)…

Optimization and Control · Mathematics 2022-10-27 Dan Garber , Ron Fisher

In this article a unified approach to iterative soft-thresholding algorithms for the solution of linear operator equations in infinite dimensional Hilbert spaces is presented. We formulate the algorithm in the framework of generalized…

Functional Analysis · Mathematics 2010-10-26 Kristian Bredies , Dirk A. Lorenz

Dynamic optimization of mean and variance in Markov decision processes (MDPs) is a long-standing challenge caused by the failure of dynamic programming. In this paper, we propose a new approach to find the globally optimal policy for…

Optimization and Control · Mathematics 2023-02-28 Li Xia , Shuai Ma

There are no computationally feasible algorithms that provide solutions to the finite horizon Risk-sensitive Constrained Markov Decision Process (Risk-CMDP) problem, even for problems with moderate horizon. With an aim to design the same,…

Optimization and Control · Mathematics 2023-03-27 Vartika Singh , Veeraruna Kavitha

Softmax feedback systems are a common mathematical core of entropy-regularized reinforcement learning, logit game dynamics, population choice, and mean-field variational updates. Their central stability question is simple: when does a…

Machine Learning · Computer Science 2026-05-18 Tongxi Wang

The reinforcement learning algorithm SARSA combined with linear function approximation has been shown to converge for infinite horizon discounted Markov decision problems (MDPs). In this paper, we investigate the convergence of the…

Machine Learning · Computer Science 2023-06-08 Lina Palmborg

Policy gradient algorithms have been widely applied to Markov decision processes and reinforcement learning problems in recent years. Regularization with various entropy functions is often used to encourage exploration and improve…

Machine Learning · Computer Science 2023-06-09 Haoya Li , Samarth Gupta , Hsiangfu Yu , Lexing Ying , Inderjit Dhillon

This paper is on learning the Kalman gain by policy optimization method. Firstly, we reformulate the finite-horizon Kalman filter as a policy optimization problem of the dual system. Secondly, we obtain the global linear convergence of…

Optimization and Control · Mathematics 2023-10-30 Haoran Li , Yuan-Hua Ni

Efficient exploration is a central problem in reinforcement learning and is often formalized as maximizing the entropy of the state-action occupancy measure. While unconstrained maximum-entropy exploration is relatively well understood,…

Machine Learning · Computer Science 2026-05-01 Florian Wolf , Ilyas Fatkhullin , Niao He

Federated reinforcement learning (RL) enables collaborative decision making of multiple distributed agents without sharing local data trajectories. In this work, we consider a multi-task setting, in which each agent has its own private…

Machine Learning · Computer Science 2024-08-19 Tong Yang , Shicong Cen , Yuting Wei , Yuxin Chen , Yuejie Chi

Owing to the growth of interest in Reinforcement Learning in the last few years, gradient based policy control methods have been gaining popularity for Control problems as well. And rightly so, since gradient policy methods have the…

Machine Learning · Computer Science 2021-12-01 Santanu Rathod , Manoj Bhadu , Abir De

In this paper, we study the controllability and stabilizability properties of the Kolmogorov forward equation of a continuous time Markov chain (CTMC) evolving on a finite state space, using the transition rates as the control parameters.…

Systems and Control · Computer Science 2017-03-29 Karthik Elamvazhuthi , Vaibhav Deshmukh , Matthias Kawski , Spring Berman

Gradient descent dynamics on the deep matrix factorization problem is extensively studied as a simplified theoretical model for deep neural networks. Although the convergence theory for two-layer matrix factorization is well-established, no…

Optimization and Control · Mathematics 2025-11-20 Minrui Luo , Weihang Xu , Xiang Gao , Maryam Fazel , Simon Shaolei Du

Mean-field Langevin dynamics (MFLD) minimizes an entropy-regularized nonlinear convex functional defined over the space of probability distributions. MFLD has gained attention due to its connection with noisy gradient descent for mean-field…

Machine Learning · Computer Science 2024-10-31 Atsushi Nitanda
‹ Prev 1 3 4 5 6 7 10 Next ›