English
Related papers

Related papers: Convergence and sample complexity of natural polic…

200 papers

Constrained Reinforcement Learning (CRL) addresses sequential decision-making problems where agents are required to achieve goals by maximizing the expected return while meeting domain-specific constraints. In this setting, policy-based…

Machine Learning · Computer Science 2025-06-09 Alessandro Montenegro , Leonardo Cesani , Marco Mussi , Matteo Papini , Alberto Maria Metelli

Binary optimization has a wide range of applications in combinatorial optimization problems such as MaxCut, MIMO detection, and MaxSAT. However, these problems are typically NP-hard due to the binary constraints. We develop a novel…

Optimization and Control · Mathematics 2023-07-04 Cheng Chen , Ruitao Chen , Tianyou Li , Ruichen Ao , Zaiwen Wen

Safety is a fundamental challenge in reinforcement learning (RL), particularly in real-world applications such as autonomous driving, robotics, and healthcare. To address this, Constrained Markov Decision Processes (CMDPs) are commonly used…

Machine Learning · Computer Science 2026-02-18 Chang Liu , Yunfan Li , Lin F. Yang

We study robust Markov decision processes (RMDPs) with general policy parameterization under s-rectangular and non-rectangular uncertainty sets. Prior work is largely limited to tabular policies, and hence either lacks sample complexity…

Machine Learning · Computer Science 2026-02-13 Anirudh Satheesh , Ziyi Chen , Furong Huang , Heng Huang

This work proposes an accelerated primal-dual dynamical system for affine constrained convex optimization and presents a class of primal-dual methods with nonergodic convergence rates. In continuous level, exponential decay of a novel…

Optimization and Control · Mathematics 2022-04-12 Hao Luo

The linear primal-dual hybrid gradient (PDHG) method is a first-order method that splits convex optimization problems with saddle-point structure into smaller subproblems. Unlike those obtained in most splitting methods, these subproblems…

Optimization and Control · Mathematics 2022-04-05 Jérôme Darbon , Gabriel P. Langlois

In this work, we investigate the margin-maximization bias exhibited by gradient-based algorithms in classifying linearly separable data. We present an in-depth analysis of the specific properties of the velocity field associated with…

Machine Learning · Computer Science 2024-12-30 Mingze Wang , Zeping Min , Lei Wu

In this paper, we present a new policy gradient (PG) methods, namely the block policy mirror descent (BPMD) method for solving a class of regularized reinforcement learning (RL) problems with (strongly)-convex regularizers. Compared to the…

Machine Learning · Computer Science 2022-09-20 Guanghui Lan , Yan Li , Tuo Zhao

We propose a new randomized algorithm for solving convex optimization problems that have a large number of constraints (with high probability). Existing methods like interior-point or Newton-type algorithms are hard to apply to such…

Optimization and Control · Mathematics 2020-03-25 Bo Wei , William B. Haskell , Sixiang Zhao

We study the global convergence of policy gradient for infinite-horizon entropy-regularized Markov decision processes (MDPs) with continuous state and action spaces. We consider log-linear softmax policies with linear function…

Machine Learning · Computer Science 2026-05-26 Ziyue Chen , David Šiška , Lukasz Szpruch

While the techniques in optimal control theory are often model-based, the policy optimization (PO) approach directly optimizes the performance metric of interest. Even though it has been an essential approach for reinforcement learning…

Optimization and Control · Mathematics 2022-11-23 Feiran Zhao , Keyou You , Tamer Başar

We consider the problem of learning an $\varepsilon$-optimal policy in a general class of continuous-space Markov decision processes (MDPs) having smooth Bellman operators. Given access to a generative model, we achieve rate-optimal sample…

Machine Learning · Computer Science 2024-05-13 Davide Maran , Alberto Maria Metelli , Matteo Papini , Marcello Restelli

This paper develops a distributed model predictive control (DMPC) strategy for a class of discrete-time linear systems with consideration of globally coupled constraints. The DMPC under study is based on the dual problem concerning all…

Optimization and Control · Mathematics 2019-07-25 Yanxu Su , Yang Shi , Changyin Sun

Conic optimization is the minimization of a differentiable convex objective function subject to conic constraints. We propose a novel primal-dual first-order method for conic optimization, named proportional-integral projected gradient…

Optimization and Control · Mathematics 2021-12-15 Yue Yu , Purnanand Elango , Ufuk Topcu , Behçet Açıkmeşe

We present a new algorithm for solving optimization problems with objective functions that are the sum of a smooth function and a (potentially) nonsmooth regularization function, and nonlinear equality constraints. The algorithm may be…

Optimization and Control · Mathematics 2024-04-12 Yutong Dai , Xiaoyi Qu , Daniel P. Robinson

Minimax problems have recently attracted a lot of research interests. A few efforts have been made to solve decentralized nonconvex strongly-concave (NCSC) minimax-structured optimization; however, all of them focus on smooth problems with…

Optimization and Control · Mathematics 2023-04-06 Yangyang Xu

This paper proposes a novel termination criterion, termed the advantage gap function, for finite state and action Markov decision processes (MDP) and reinforcement learning (RL). By incorporating this advantage gap function into the design…

Machine Learning · Computer Science 2026-03-24 Caleb Ju , Guanghui Lan

We develop a framework for convexifying a fairly general class of optimization problems. Under additional assumptions, we analyze the suboptimality of the solution to the convexified problem relative to the original nonconvex problem and…

Systems and Control · Computer Science 2014-06-04 Krishnamurthy Dvijotham , Maryam Fazel , Emanuel Todorov

This paper develops a continuous-time primal-dual accelerated method with an increasing damping coefficient for a class of convex optimization problems with affine equality constraints. This paper analyzes critical values for parameters in…

Optimization and Control · Mathematics 2022-02-16 Xianlin Zeng , Jinlong Lei , Jie Chen

In the optimization of dynamic systems, the variables typically have constraints. Such problems can be modeled as a Constrained Markov Decision Process (CMDP). This paper considers the peak Constrained Markov Decision Process (PCMDP), where…

Optimization and Control · Mathematics 2022-06-15 Qinbo Bai , Vaneet Aggarwal , Ather Gattami