English
Related papers

Related papers: Convex Q-Learning, Part 1: Deterministic Optimal C…

200 papers

Watkins' and Dayan's Q-learning is a model-free reinforcement learning algorithm that iteratively refines an estimate for the optimal action-value function of an MDP by stochastically "visiting" many state-ation pairs [Watkins and Dayan,…

Machine Learning · Computer Science 2021-08-09 Matthew T. Regehr , Alex Ayoub

In this letter, we discuss the problem of optimal control for affine systems in the context of data-driven linear programming. First, we introduce a unified framework for the fixed point characterization of the value function, Q-function…

Systems and Control · Electrical Eng. & Systems 2022-07-12 Andrea Martinelli , Matilde Gargiani , Marina Draskovic , John Lygeros

Q-learning has become an important part of the reinforcement learning toolkit since its introduction in the dissertation of Chris Watkins in the 1980s. The purpose of this paper is in part a tutorial on stochastic approximation and…

Machine Learning · Computer Science 2023-08-22 Sean Meyn

With the widespread adoption of machine learning systems, the need to curtail their behavior has become increasingly apparent. This is evidenced by recent advancements towards developing models that satisfy robustness, safety, and fairness…

Machine Learning · Computer Science 2024-03-19 Juan Elenter , Luiz F. O. Chamon , Alejandro Ribeiro

We study the safe reinforcement learning problem with nonlinear function approximation, where policy optimization is formulated as a constrained optimization problem with both the objective and the constraint being nonconvex functions. For…

Machine Learning · Computer Science 2019-10-29 Ming Yu , Zhuoran Yang , Mladen Kolar , Zhaoran Wang

The goal of this paper is to investigate new and simple convergence analysis of dynamic programming for linear quadratic regulator problem of discrete-time linear time-invariant systems. In particular, bounds on errors are given in terms of…

Optimization and Control · Mathematics 2021-06-18 Donghwan Lee

The linear programming (LP) approach has a long history in the theory of approximate dynamic programming. When it comes to computation, however, the LP approach often suffers from poor scalability. In this work, we introduce a relaxed…

Systems and Control · Electrical Eng. & Systems 2020-12-01 Andrea Martinelli , Matilde Gargiani , John Lygeros

Many problems of theoretical and practical interest involve finding an optimum over a family of convex functions. For instance, finding the projection on the convex functions in $H^k(\Omega)$, and optimizing functionals arising from some…

Numerical Analysis · Mathematics 2008-04-11 Néstor E. Aguilera , Pedro Morin

Convex quadratic programs (QPs) constitute a fundamental computational primitive across diverse domains including financial optimization, control systems, and machine learning. The alternating direction method of multipliers (ADMM) has…

Optimization and Control · Mathematics 2025-05-15 Xi Gao , Jinxin Xiong , Linxin Yang , Akang Wang , Weiwei Xu , Jiang Xue

Learning to make decisions from observed data in dynamic environments remains a problem of fundamental importance in a number of fields, from artificial intelligence and robotics, to medicine and finance. This paper concerns the problem of…

Machine Learning · Statistics 2018-06-04 Jack Umenberger , Thomas B. Schön

The approximation capabilities of Deep Q-Networks (DQNs) are commonly justified by general Universal Approximation Theorems (UATs) that do not leverage the intrinsic structural properties of the optimal Q-function, the solution to a Bellman…

Machine Learning · Computer Science 2025-05-12 Qian Qi

We establish a continuous-time framework for analyzing Deep Q-Networks (DQNs) via stochastic control and Forward-Backward Stochastic Differential Equations (FBSDEs). Considering a continuous-time Markov Decision Process (MDP) driven by a…

Machine Learning · Computer Science 2025-05-06 Qian Qi

Motivated by applications in optimization and machine learning, we consider stochastic quasi-Newton (SQN) methods for solving stochastic optimization problems. In the literature, the convergence analysis of these algorithms relies on strong…

Optimization and Control · Mathematics 2016-03-16 Farzad Yousefian , Angelia Nedić , Uday V. Shanbha

Optimal control theory and machine learning techniques are combined to formulate and solve in closed form an optimal control formulation of online learning from supervised examples with regularization of the updates. The connections with…

Optimization and Control · Mathematics 2016-12-15 Giorgio Gnecco , Alberto Bemporad , Marco Gori , Marcello Sanguineti

We study the expressibility and learnability of convex optimization solution functions and their multi-layer architectural extension. The main results are: \emph{(1)} the class of solution functions of linear programming (LP) and quadratic…

Machine Learning · Computer Science 2022-12-05 Ming Jin , Vanshaj Khattar , Harshal Kaushik , Bilgehan Sel , Ruoxi Jia

We deal with the convergence of the value function of an approximate control problem with uncertain dynamics to the value function of a nonlinear optimal control problem. The assumptions on the dynamics and the costs are rather general and…

Optimization and Control · Mathematics 2021-05-31 Andrea Pesare , Michele Palladino , Maurizio Falcone

We consider joint optimization and learning problems arising in real-time decision systems. While most existing work focuses primarily on convex, revenue-based objectives, we extend this line of research to multi-objective formulations. In…

Optimization and Control · Mathematics 2026-04-14 Zijun Li , Aswin Kannan

In this paper, we propose Q-learning algorithms for continuous-time deterministic optimal control problems with Lipschitz continuous controls. Our method is based on a new class of Hamilton-Jacobi-Bellman (HJB) equations derived from…

Machine Learning · Computer Science 2020-10-28 Jeongho Kim , Jaeuk Shin , Insoon Yang

Quadratic programming is a workhorse of modern nonlinear optimization, control, and data science. Although regularized methods offer convergence guarantees under minimal assumptions on the problem data, they can exhibit the slow…

Optimization and Control · Mathematics 2026-05-18 Jeremy Bertoncini , Alberto De Marchi , Matthias Gerdts , Simon Gottschalk

Temporal-difference learning (TD), coupled with neural networks, is among the most fundamental building blocks of deep reinforcement learning. However, due to the nonlinearity in value function approximation, such a coupling leads to…

Machine Learning · Computer Science 2020-04-16 Qi Cai , Zhuoran Yang , Jason D. Lee , Zhaoran Wang