English
Related papers

Related papers: Variance-Reduced Off-Policy TDC Learning: Non-Asym…

200 papers

The goal of this paper is to study a distributed version of the gradient temporal-difference (GTD) learning algorithm for multi-agent Markov decision processes (MDPs). The temporal difference (TD) learning is a reinforcement learning (RL)…

Optimization and Control · Mathematics 2018-08-23 Donghwan Lee , Hyungjin Yoon , Naira Hovakimyan

In large-scale distributed machine learning, recent works have studied the effects of compressing gradients in stochastic optimization to alleviate the communication bottleneck. These works have collectively revealed that stochastic…

Machine Learning · Computer Science 2024-06-05 Aritra Mitra , George J. Pappas , Hamed Hassani

This article derives lower bounds on the convergence rate of continuous-time gradient-based optimization algorithms. The algorithms are subjected to a time-normalization constraint that avoids a reparametrization of time in order to make…

Optimization and Control · Mathematics 2020-08-04 Michael Muehlebach , Michael I. Jordan

Graph Convolutional Networks (GCNs) have achieved impressive empirical advancement across a wide variety of semi-supervised node classification tasks. Despite their great success, training GCNs on large graphs suffers from computational and…

Machine Learning · Computer Science 2021-11-02 Weilin Cong , Morteza Ramezani , Mehrdad Mahdavi

In this paper we propose an efficient variance reduction approach for additive functionals of Markov chains relying on a novel discrete time martingale representation. Our approach is fully non-asymptotic and does not require the knowledge…

Computation · Statistics 2021-12-22 D. Belomestny , E. Moulines , S. Samsonov

Temporal-difference learning with function approximation can be unstable under off-policy sampling. TDC stabilizes off-policy TD through an auxiliary covariance correction, and TDRC further regularizes this correction in a single-timescale…

Artificial Intelligence · Computer Science 2026-05-29 Xingguo Chen , Zhiang He , Yuchen Shen , Shangdong Yang , Chao Li , Guang Yang , Wenhao Wang

This paper presents an off-policy Gaussian Predictive Control (GPC) framework aimed at solving optimal control problems with a smaller computational footprint, thereby facilitating real-time applicability while ensuring critical safety…

Robotics · Computer Science 2026-03-19 Shiva Kumar Tekumatla , Varun Gampa , Siavash Farzan

We quantify the efficiency of temporal difference (TD) learning over the direct, or Monte Carlo (MC), estimator for policy evaluation in reinforcement learning, with an emphasis on estimation of quantities related to rare events. Policy…

Machine Learning · Computer Science 2025-01-17 Xiaoou Cheng , Jonathan Weare

Continuous-time generative models, such as diffusion models, flow matching, and rectified flow, learn time-dependent vector fields but are typically trained with objectives that treat timesteps independently, leading to high estimator…

Machine Learning · Computer Science 2026-02-23 Chika Maduabuchi , Jindong Wang

This paper is devoted to the distributed continuous-time optimization problem with time-varying objective functions and time-varying nonlinear inequality constraints. Different from most studied distributed optimization problems with…

Optimization and Control · Mathematics 2020-09-08 Shan Sun , Wei Ren

Variance reduction is a family of powerful mechanisms for stochastic optimization that appears to be helpful in many machine learning tasks. It is based on estimating the exact gradient with some recursive sequences. Previously, many papers…

Optimization and Control · Mathematics 2025-11-07 Aleksandr Shestakov , Valery Parfenov , Aleksandr Beznosikov

To accumulate knowledge and improve its policy of behaviour, a reinforcement learning agent can learn `off-policy' about policies that differ from the policy used to generate its experience. This is important to learn counterfactuals, or…

Machine Learning · Computer Science 2022-02-03 Simon Schmitt , John Shawe-Taylor , Hado van Hasselt

We prove a non-asymptotic central limit theorem for vector-valued martingale differences using Stein's method, and use Poisson's equation to extend the result to functions of Markov Chains. We then show that these results can be applied to…

Probability · Mathematics 2026-02-10 R. Srikant

Off-policy learning enables a reinforcement learning (RL) agent to reason counterfactually about policies that are not executed and is one of the most important ideas in RL. It, however, can lead to instability when combined with function…

Machine Learning · Computer Science 2025-03-03 Xiaochi Qian , Shangtong Zhang

Policy gradient methods are widely adopted reinforcement learning algorithms for tasks with continuous action spaces. These methods succeeded in many application domains, however, because of their notorious sample inefficiency their use…

Machine Learning · Statistics 2024-02-20 Davide Mambelli , Stephan Bongers , Onno Zoeter , Matthijs T. J. Spaan , Frans A. Oliehoek

Recent non-asymptotic analyses have substantially advanced the theory of distributional policy evaluation, but they largely concern synchronous full-state updates under a generative model, model-based estimators, accelerated variants, or…

Machine Learning · Computer Science 2026-05-11 Ege C. Kaya , Abolfazl Hashemi

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

TD(0) is one of the most commonly used algorithms in reinforcement learning. Despite this, there is no existing finite sample analysis for TD(0) with function approximation, even for the linear case. Our work is the first to provide such…

Artificial Intelligence · Computer Science 2017-12-12 Gal Dalal , Balázs Szörényi , Gugan Thoppe , Shie Mannor

The use of target networks has been a popular and key component of recent deep Q-learning algorithms for reinforcement learning, yet little is known from the theory side. In this work, we introduce a new family of target-based temporal…

Machine Learning · Computer Science 2019-09-24 Donghwan Lee , Niao He

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
‹ Prev 1 8 9 10 Next ›