English
Related papers

Related papers: On Convergence of Gradient Expected Sarsa($\lambda…

200 papers

Off-policy learning is powerful for reinforcement learning. However, the high variance of off-policy evaluation is a critical challenge, which causes off-policy learning falls into an uncontrolled instability. In this paper, for reducing…

Machine Learning · Computer Science 2019-09-09 Long Yang , Yu Zhang , Jun Wen , Qian Zheng , Pengfei Li , Gang Pan

In this paper, we analyze the convergence rate of the gradient temporal difference learning (GTD) family of algorithms. Previous analyses of this class of algorithms use ODE techniques to prove asymptotic convergence, and to the best of our…

Machine Learning · Computer Science 2020-07-06 Bo Liu , Ji Liu , Mohammad Ghavamzadeh , Sridhar Mahadevan , Marek Petrik

Off-policy learning is key to scaling up reinforcement learning as it allows to learn about a target policy from the experience generated by a different behavior policy. Unfortunately, it has been challenging to combine off-policy learning…

Machine Learning · Computer Science 2019-01-04 Ahmed Touati , Pierre-Luc Bacon , Doina Precup , Pascal Vincent

Full-sampling (e.g., Q-learning) and pure-expectation (e.g., Expected Sarsa) algorithms are efficient and frequently used techniques in reinforcement learning. Q$(\sigma,\lambda)$ is the first approach unifies them with eligibility trace…

Machine Learning · Computer Science 2019-09-09 Long Yang , Yu Zhang , Qian Zheng , Pengfei Li , Gang Pan

Gradient compression is of growing interests for solving constrained optimization problems including compressed sensing, noisy recovery and matrix completion under limited communication resources and storage costs. Convergence analysis of…

Optimization and Control · Mathematics 2024-10-30 Zhaoyue Xia , Jun Du , Chunxiao Jiang , H. Vincent Poor , Yong Ren

We consider the traffic control problem of dynamic routing over parallel servers, which arises in a variety of engineering systems such as transportation and data transmission. We propose a semi-gradient, on-policy algorithm that learns an…

Machine Learning · Computer Science 2025-03-20 Yidan Wu , Yu Yu , Jianan Zhang , Li Jin

We consider off-policy temporal-difference (TD) learning methods for policy evaluation in Markov decision processes with finite spaces and discounted reward criteria, and we present a collection of convergence results for several…

Machine Learning · Computer Science 2018-03-30 Huizhen Yu

Stochastic optimization naturally appear in many application areas, including machine learning. Our goal is to go further in the analysis of the Stochastic Average Gradient Accelerated (SAGA) algorithm. To achieve this, we introduce a new…

Optimization and Control · Mathematics 2024-10-08 Luis Fredes , Bernard Bercu , Eméric Gbaguidi

This paper considers the problem of designing accelerated gradient-based algorithms for optimization and saddle-point problems. The class of objective functions is defined by a generalized sector condition. This class of functions contains…

Optimization and Control · Mathematics 2020-11-17 Dennis Gramlich , Christian Ebenbauer , Carsten W. Scherer

We study the iteration complexity of the optimistic gradient descent-ascent (OGDA) method and the extra-gradient (EG) method for finding a saddle point of a convex-concave unconstrained min-max problem. To do so, we first show that both…

Optimization and Control · Mathematics 2020-09-30 Aryan Mokhtari , Asuman Ozdaglar , Sarath Pattathil

Nonconvex optimization underlies many modern machine learning and control tasks, where saddle points pose the dominant obstacle to reliable convergence in high-dimensional settings. Escaping these saddle points deterministically using…

Optimization and Control · Mathematics 2026-05-13 Liraz Mudrik , Isaac Kaminer , Sean Kragelund , Abram H. Clark

In this work, we propose new adaptive step size strategies that improve several stochastic gradient methods. Our first method (StoPS) is based on the classical Polyak step size (Polyak, 1987) and is an extension of the recent development of…

Machine Learning · Computer Science 2022-08-11 Samuel Horváth , Konstantin Mishchenko , Peter Richtárik

Stochastic gradient descent (SGD) is the workhorse of large-scale learning, yet classical analyses rely on assumptions that can be either too strong (bounded variance) or too coarse (uniform noise). The expected smoothness (ES) condition…

Machine Learning · Computer Science 2025-10-28 Yuta Kawamoto , Hideaki Iiduka

We present a family of algorithms, called descent algorithms, for optimizing convex and non-convex functions. We also introduce a new first-order algorithm, called rescaled gradient descent (RGD), and show that RGD achieves a faster…

Optimization and Control · Mathematics 2020-01-07 Ashia Wilson , Lester Mackey , Andre Wibisono

In this paper, we introduce proximal gradient temporal difference learning, which provides a principled way of designing and analyzing true stochastic gradient temporal difference learning algorithms. We show how gradient TD (GTD)…

Machine Learning · Computer Science 2020-06-09 Bo Liu , Ian Gemp , Mohammad Ghavamzadeh , Ji Liu , Sridhar Mahadevan , Marek Petrik

Subspace learning and matrix factorization problems have great many applications in science and engineering, and efficient algorithms are critical as dataset sizes continue to grow. Many relevant problem formulations are non-convex, and in…

Numerical Analysis · Computer Science 2022-02-22 Dejiao Zhang , Laura Balzano

We introduce a novel algorithm for gradient-based optimization of stochastic objective functions. The method may be seen as a variant of SGD with momentum equipped with an adaptive learning rate automatically adjusted by an 'energy'…

Optimization and Control · Mathematics 2022-03-24 Hailiang Liu , Xuping Tian

Gradient-based first-order convex optimization algorithms find widespread applicability in a variety of domains, including machine learning tasks. Motivated by the recent advances in fixed-time stability theory of continuous-time dynamical…

Machine Learning · Computer Science 2023-10-24 Mayank Baranwal , Param Budhraja , Vishal Raj , Ashish R. Hota

Many popular adaptive gradient methods such as Adam and RMSProp rely on an exponential moving average (EMA) to normalize their stepsizes. While the EMA makes these methods highly responsive to new gradient information, recent research has…

Machine Learning · Computer Science 2021-10-13 Brett Daley , Christopher Amato

In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good policy evaluation method, the RL algorithms…

Machine Learning · Computer Science 2018-09-25 Yue Wang , Wei Chen , Yuting Liu , Zhi-Ming Ma , Tie-Yan Liu
‹ Prev 1 2 3 10 Next ›