English
Related papers

Related papers: Policy Gradient Methods for the Cost-Constrained L…

200 papers

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

A method is presented for solving the discrete-time finite-horizon Linear Quadratic Regulator (LQR) problem subject to auxiliary linear equality constraints, such as fixed end-point constraints. The method explicitly determines an affine…

Systems and Control · Computer Science 2018-09-18 Forrest Laine , Claire Tomlin

Safe reinforcement learning (RL) is a popular and versatile paradigm to learn reward-maximizing policies with safety guarantees. Previous works tend to express the safety constraints in an expectation form due to the ease of implementation,…

Machine Learning · Computer Science 2024-12-18 Chenglin Li , Guangchun Ruan , Hua Geng

Lagrangian methods are widely used algorithms for constrained optimization problems, but their learning dynamics exhibit oscillations and overshoot which, when applied to safe reinforcement learning, leads to constraint-violating behavior…

Optimization and Control · Mathematics 2020-07-09 Adam Stooke , Joshua Achiam , Pieter Abbeel

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

Constrained optimization provides a common framework for dealing with conflicting objectives in reinforcement learning (RL). In most of these settings, the objectives (and constraints) are expressed though the expected accumulated reward.…

Machine Learning · Computer Science 2025-12-03 Jane H. Lee , Baturay Saglam , Spyridon Pougkakiotis , Amin Karbasi , Dionysis Kalogerias

The objective in a traditional reinforcement learning (RL) problem is to find a policy that optimizes the expected value of a performance metric such as the infinite-horizon cumulative discounted or long-run average cost/reward. In…

Machine Learning · Computer Science 2022-05-25 Prashanth L. A. , Michael Fu

We consider the Linear-Quadratic-Regulator (LQR) problem in terms of optimizing a real-valued matrix function over the set of feedback gains. Such a setup facilitates examining the implications of a natural initial-state independent…

Systems and Control · Electrical Eng. & Systems 2019-07-31 Jingjing Bu , Afshin Mesbahi , Maryam Fazel , Mehran Mesbahi

A popular framework for enforcing safe actions in Reinforcement Learning (RL) is Constrained RL, where trajectory based constraints on expected cost (or other cost measures) are employed to enforce safety and more importantly these…

Machine Learning · Computer Science 2024-08-09 Huy Hoang , Tien Mai , Pradeep Varakantham

This paper proposes a safe reinforcement learning (RL) algorithm that approximately solves the state-constrained optimal control problem for continuous-time uncertain nonlinear systems. We formulate the safe RL problem as the minimization…

Systems and Control · Electrical Eng. & Systems 2025-06-26 Soutrik Bandyopadhyay , Shubhendu Bhasin

We study constrained reinforcement learning (CRL) from a novel perspective by setting constraints directly on state density functions, rather than the value functions considered by previous works. State density has a clear physical and…

Machine Learning · Computer Science 2021-06-25 Zengyi Qin , Yuxiao Chen , Chuchu Fan

We study a primal-dual (PD) reinforcement learning (RL) algorithm for online constrained Markov decision processes (CMDPs). Despite its widespread practical use, the existing theoretical literature on PD-RL algorithms for this problem only…

With the outstanding performance of policy gradient (PG) method in the reinforcement learning field, the convergence theory of it has aroused more and more interest recently. Meanwhile, the significant importance and abundant theoretical…

Optimization and Control · Mathematics 2024-04-19 Xinpei Zhang , Guangyan Jia

Online safe reinforcement learning (RL) involves training a policy that maximizes task efficiency while satisfying constraints via interacting with the environments. In this paper, our focus lies in addressing the complex challenges…

Machine Learning · Computer Science 2023-12-27 Yihang Yao , Zuxin Liu , Zhepeng Cen , Peide Huang , Tingnan Zhang , Wenhao Yu , Ding Zhao

Policy gradient (PG) methods are the backbone of many reinforcement learning algorithms due to their good performance in policy optimization problems. As a gradient-based approach, PG methods typically rely on knowledge of the system…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Bowen Song , Andrea Iannelli

Safety is critical when applying reinforcement learning (RL) to real-world problems. As a result, safe RL has emerged as a fundamental and powerful paradigm for optimizing an agent's policy while incorporating notions of safety. A prevalent…

Machine Learning · Computer Science 2024-05-09 Akifumi Wachi , Xun Shen , Yanan Sui

We study the convergence of model-based policy gradient for the deterministic, scalar, discounted linear-quadratic regulator when the controller is an overparameterized one-hidden-layer ReLU network without biases. Although the optimal LQR…

Optimization and Control · Mathematics 2026-04-27 Jhojan A. Rodriguez-Gil , César A. Uribe

We study the computational complexity certification of inexact gradient augmented Lagrangian methods for solving convex optimization problems with complicated constraints. We solve the augmented Lagrangian dual problem that arises from the…

Optimization and Control · Mathematics 2013-02-19 Valentin Nedelcu , Ion Necoara , Quoc Tran Dinh

Ensuring the safety of Reinforcement Learning (RL) is crucial for its deployment in real-world applications. Nevertheless, managing the trade-off between reward and safety during exploration presents a significant challenge. Improving…

Machine Learning · Computer Science 2025-03-04 Shangding Gu , Bilgehan Sel , Yuhao Ding , Lu Wang , Qingwei Lin , Ming Jin , Alois Knoll

We study reinforcement learning by combining recent advances in regularized linear programming formulations with the classical theory of stochastic approximation. Motivated by the challenge of designing algorithms that leverage off-policy…

Optimization and Control · Mathematics 2026-04-15 Axel Friedrich Wolter , Tobias Sutter