English
Related papers

Related papers: Convergence of Dynamic Programming on the Semidefi…

200 papers

Although Q-learning is one of the most successful algorithms for finding the best action-value function (and thus the optimal policy) in reinforcement learning, its implementation often suffers from large overestimation of Q-function values…

Machine Learning · Computer Science 2020-10-13 Huaqing Xiong , Lin Zhao , Yingbin Liang , Wei Zhang

Achieving convergence of multiple learning agents in general $N$-player games is imperative for the development of safe and reliable machine learning (ML) algorithms and their application to autonomous systems. Yet it is known that, outside…

Computer Science and Game Theory · Computer Science 2023-01-24 Aamal Abbas Hussain , Francesco Belardinelli , Georgios Piliouras

We expose in a tutorial fashion the mechanisms which underlie the synthesis of optimization algorithms based on dynamic integral quadratic constraints. We reveal how these tools from robust control allow to design accelerated gradient…

Optimization and Control · Mathematics 2023-09-18 Carsten W. Scherer , Christian Ebenbauer , Tobias Holicki

Though switched dynamical systems have shown great utility in modeling a variety of physical phenomena, the construction of an optimal control of such systems has proven difficult since it demands some type of optimal mode scheduling. In…

Optimization and Control · Mathematics 2014-02-04 Ramanarayan Vasudevan , Humberto Gonzalez , Ruzena Bajcsy , S. Shankar Sastry

This paper introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages…

Systems and Control · Electrical Eng. & Systems 2023-04-03 Victor G. Lopez , Mohammad Alsalti , Matthias A. Müller

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

This paper studies a fundamental problem in convex optimization, which is to solve semidefinite programming (SDP) with high accuracy. This paper follows from the existing robust SDP-based interior point method analysis due to [Huang, Jiang,…

Quantum Physics · Physics 2023-02-08 Baihe Huang , Shunhua Jiang , Zhao Song , Runzhou Tao , Ruizhe Zhang

In this paper, we will deal with a Linear Quadratic Optimal Control problem with unknown dynamics. As a modeling assumption, we will suppose that the knowledge that an agent has on the current system is represented by a probability…

Optimization and Control · Mathematics 2022-01-13 Andrea Pesare , Michele Palladino , Maurizio Falcone

Q-learning has long been one of the most popular reinforcement learning algorithms, and theoretical analysis of Q-learning has been an active research topic for decades. Although researches on asymptotic convergence analysis of Q-learning…

Artificial Intelligence · Computer Science 2022-07-26 Han-Dong Lim , Donghwan Lee

It is well-known that by adding integrality constraints to the semidefinite programming (SDP) relaxation of the max-cut problem, the resulting integer semidefinite program is an exact formulation of the problem. In this paper we show…

Optimization and Control · Mathematics 2023-11-09 Frank de Meijer , Renata Sotirov

We analyze the convergence rate of various momentum-based optimization algorithms from a dynamical systems point of view. Our analysis exploits fundamental topological properties, such as the continuous dependence of iterates on their…

Optimization and Control · Mathematics 2021-04-13 Michael Muehlebach , Michael I. Jordan

We develop a discrete-time optimal control framework for systems evolving on Lie groups. Our work generalizes the original Differential Dynamic Programming method, by employing a coordinate-free, Lie-theoretic approach for its derivation. A…

Optimization and Control · Mathematics 2018-09-24 George I. Boutselis , Evangelos Theodorou

This manuscript develops a new framework to analyze and design iterative optimization algorithms built on the notion of Integral Quadratic Constraints (IQC) from robust control theory. IQCs provide sufficient conditions for the stability of…

Optimization and Control · Mathematics 2021-05-27 Laurent Lessard , Benjamin Recht , Andrew Packard

Correspondence problems are often modelled as quadratic optimization problems over permutations. Common scalable methods for approximating solutions of these NP-hard problems are the spectral relaxation for non-convex energies and the…

Graphics · Computer Science 2017-05-18 Nadav Dym , Haggai Maron , Yaron Lipman

This paper proposes a general formulation for temporal parallelisation of dynamic programming for optimal control problems. We derive the elements and associative operators to be able to use parallel scans to solve these problems with…

Optimization and Control · Mathematics 2022-01-25 Simo Särkkä , Ángel F. García-Fernández

This paper studies a discrete-time stochastic control problem with linear quadratic criteria over an infinite-time horizon. We focus on a class of control systems whose system matrices are associated with random parameters involving unknown…

Optimization and Control · Mathematics 2022-01-17 Zhaorong Zhang , Juanjuan Xu , Xun Li

In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm…

Machine Learning · Computer Science 2011-09-09 Mohammad Gheshlaghi Azar , Vicenc Gomez , Hilbert J. Kappen

This work theoretically studies a ubiquitous reinforcement learning policy for controlling the canonical model of continuous-time stochastic linear-quadratic systems. We show that randomized certainty equivalent policy addresses the…

Machine Learning · Computer Science 2022-08-23 Mohamad Kazem Shirani Faradonbeh

The framework of Integral Quadratic Constraints (IQC) reduces the computation of upper bounds on the convergence rate of several optimization algorithms to a semi-definite program (SDP). In the case of over-relaxed Alternating Direction…

Machine Learning · Statistics 2018-03-06 Guilherme França , José Bento

We revisit the finite time analysis of policy gradient methods in the one of the simplest settings: finite state and action MDPs with a policy class consisting of all stochastic policies and with exact gradient evaluations. There has been…

Machine Learning · Computer Science 2021-12-14 Jalaj Bhandari , Daniel Russo
‹ Prev 1 4 5 6 7 8 10 Next ›