English
Related papers

Related papers: Double Duality: Variational Primal-Dual Policy Opt…

200 papers

Monotonic Partially Observable Markov Decision Processes (POMDPs), where the system state progressively decreases until a restorative action is performed, can be used to model sequential repair problems effectively. This paper considers the…

Machine Learning · Computer Science 2025-09-17 Manav Vora , Jonas Liang , Michael N. Grussing , Melkior Ornik

The pursuit of robustness has recently been a popular topic in reinforcement learning (RL) research, yet the existing methods generally suffer from efficiency issues that obstruct their real-world implementation. In this paper, we introduce…

Machine Learning · Computer Science 2024-04-15 Yang Hu , Haitong Ma , Bo Dai , Na Li

Several attempts to dampen the curse of dimensionnality problem of the Dynamic Programming approach for solving multistage optimization problems have been investigated. One popular way to address this issue is the Stochastic Dual Dynamic…

Optimization and Control · Mathematics 2020-10-09 Marianne Akian , Jean-Philippe Chancelier , Benoît Tran

We consider a constrained Markov Decision Problem (CMDP) where the goal of an agent is to maximize the expected discounted sum of rewards over an infinite horizon while ensuring that the expected discounted sum of costs exceeds a certain…

Machine Learning · Computer Science 2024-11-01 Washim Uddin Mondal , Vaneet Aggarwal

Decision-making under distribution shift is a central challenge in reinforcement learning (RL), where training and deployment environments differ. We study this problem through the lens of robust Markov decision processes (RMDPs), which…

Machine Learning · Computer Science 2025-10-17 Jingwen Gu , Yiting He , Zhishuai Liu , Pan Xu

In this paper, we consider reinforcement learning of Markov Decision Processes (MDP) with peak constraints, where an agent chooses a policy to optimize an objective and at the same time satisfy additional constraints. The agent has to take…

Optimization and Control · Mathematics 2019-12-09 Ather Gattami

We consider the problem of constrained Markov decision process (CMDP) in continuous state-actions spaces where the goal is to maximize the expected cumulative reward subject to some constraints. We propose a novel Conservative Natural…

Machine Learning · Computer Science 2024-05-20 Qinbo Bai , Amrit Singh Bedi , Vaneet Aggarwal

We consider a generic empirical composition optimization problem, where there are empirical averages present both outside and inside nonlinear loss functions. Such a problem is of interest in various machine learning applications, and…

Optimization and Control · Mathematics 2019-11-04 Adithya M. Devraj , Jianshu Chen

Lagrangian duality in mixed integer optimization is a useful framework for problems decomposition and for producing tight lower bounds to the optimal objective, but in contrast to the convex counterpart, it is generally unable to produce…

Optimization and Control · Mathematics 2014-11-10 Robin Vujanic , Peyman Mohajerin Esfahani , Paul Goulart , Sebastien Mariethoz , Manfred Morari

We study the Safe Reinforcement Learning (SRL) problem using the Constrained Markov Decision Process (CMDP) formulation in which an agent aims to maximize the expected total reward subject to a safety constraint on the expected total value…

Machine Learning · Computer Science 2020-10-27 Dongsheng Ding , Xiaohan Wei , Zhuoran Yang , Zhaoran Wang , Mihailo R. Jovanović

In this paper, we study a constrained utility maximization problem following the convex duality approach. After formulating the primal and dual problems, we construct the necessary and sufficient conditions for both the primal and dual…

Mathematical Finance · Quantitative Finance 2016-12-15 Yusong Li , Harry Zheng

We are interested in risk constraints for infinite horizon discrete time Markov decision processes (MDPs). Starting with average reward MDPs, we show that increasing concave stochastic dominance constraints on the empirical distribution of…

Optimization and Control · Mathematics 2012-06-21 William B. Haskell , Rahul Jain

We consider Lagrangian duality based approaches to design and analyze algorithms for online energy-efficient scheduling. First, we present a primal-dual framework. Our approach makes use of the Lagrangian weak duality and convexity to…

Data Structures and Algorithms · Computer Science 2014-08-06 Nguyen Kim Thang

This paper addresses the design and analysis of feedback-based online algorithms to control systems or networked systems based on performance objectives and engineering constraints that may evolve over time. The emerging time-varying convex…

Optimization and Control · Mathematics 2019-03-27 Andrey Bernstein , Emiliano Dall'Anese , Andrea Simonetto

This paper develops a primal-dual dynamical system where the coefficients are designed in closed-loop way for solving a convex optimization problem with linear equality constraints. We first introduce a ``second-order primal" +…

Optimization and Control · Mathematics 2026-03-03 Huan Zhang , Xiangkai Sun , Shengjie Li , Kok Lay Teo

Using convex combination and linesearch techniques, we introduce a novel primal-dual algorithm for solving structured convex-concave saddle point problems with a generic smooth nonbilinear coupling term. Our adaptive linesearch strategy…

Optimization and Control · Mathematics 2024-01-17 Xiaokai Chang , Junfeng Yang , Hongchao Zhang

Algorithms developed under stationary Markov Decision Processes (MDPs) often face challenges in non-stationary environments, and infinite-horizon formulations may not directly apply to finite-horizon tasks. To address these limitations, we…

Machine Learning · Computer Science 2025-12-03 Zhizuo Chen , Theodore T. Allen

By exploiting double-penalty terms for the primal subproblem, we develop a novel relaxed augmented Lagrangian method for solving a family of convex optimization problems subject to equality or inequality constraints. The method is then…

Numerical Analysis · Mathematics 2025-06-16 Jianchao Bai , Linyuan Jia , Zheng Peng

Robust Markov decision processes (MDPs) are used for applications of dynamic optimization in uncertain environments and have been studied extensively. Many of the main properties and algorithms of MDPs, such as value iteration and policy…

Optimization and Control · Mathematics 2023-12-14 Julien Grand-Clément , Marek Petrik

This paper focuses on learning a Constrained Markov Decision Process (CMDP) via general parameterized policies. We propose a Primal-Dual based Regularized Accelerated Natural Policy Gradient (PDR-ANPG) algorithm that uses entropy and…

Machine Learning · Computer Science 2026-05-04 Washim Uddin Mondal , Vaneet Aggarwal