English
Related papers

Related papers: Finite time analysis of temporal difference learni…

200 papers

Temporal-Difference (TD) learning is a standard and very successful reinforcement learning approach, at the core of both algorithms that learn the value of a given policy, as well as algorithms which learn how to improve policies.…

Machine Learning · Computer Science 2020-06-17 Mingde Zhao

Stochastic approximation (SA) is a fundamental iterative framework with broad applications in reinforcement learning and optimization. Classical analyses typically rely on martingale difference or Markov noise with bounded second moments,…

Machine Learning · Computer Science 2026-03-23 Siddharth Chandak , Anuj Yadav , Ayfer Ozgur , Nicholas Bambos

Deep Learning (DL) models can be used to tackle time series analysis tasks with great success. However, the performance of DL models can degenerate rapidly if the data are not appropriately normalized. This issue is even more apparent when…

Computational Finance · Quantitative Finance 2019-09-24 Nikolaos Passalis , Anastasios Tefas , Juho Kanniainen , Moncef Gabbouj , Alexandros Iosifidis

Tail averaging consists in averaging the last examples in a stream. Common techniques either have a memory requirement which grows with the number of samples to average, are not available at every timestep or do not accomodate growing…

Machine Learning · Computer Science 2019-02-21 Nicolas Le Roux

We are interested in understanding stability (almost sure boundedness) of stochastic approximation algorithms (SAs) driven by a `controlled Markov' process. Analyzing this class of algorithms is important, since many reinforcement learning…

Systems and Control · Computer Science 2018-05-18 Arunselvan Ramaswamy , Shalabh Bhatnagar

In many finite horizon episodic reinforcement learning (RL) settings, it is desirable to optimize for the undiscounted return - in settings like Atari, for instance, the goal is to collect the most points while staying alive in the long…

Machine Learning · Computer Science 2019-05-28 Joshua Romoff , Peter Henderson , Ahmed Touati , Emma Brunskill , Joelle Pineau , Yann Ollivier

This paper develops an unified framework to study finite-sample convergence guarantees of a large class of value-based asynchronous reinforcement learning (RL) algorithms. We do this by first reformulating the RL algorithms as…

Machine Learning · Computer Science 2023-09-06 Zaiwei Chen , Siva Theja Maguluri , Sanjay Shakkottai , Karthikeyan Shanmugam

We study the finite-time convergence of projected linear two-time-scale stochastic approximation with constant step sizes and Polyak--Ruppert averaging. We establish an explicit mean-square error bound, decomposing it into two interpretable…

Systems and Control · Electrical Eng. & Systems 2026-04-02 Yitao Bai , Thinh T. Doan , Justin Romberg

In this paper, we present a new framework to obtain tail inequalities for sums of random matrices. Compared with existing works, our tail inequalities have the following characteristics: 1) high feasibility--they can be used to study the…

Machine Learning · Computer Science 2019-10-10 Chao Zhang , Min-Hsiu Hsieh , Dacheng Tao

Temporal action detection (TAD) is an important yet challenging task in video understanding. It aims to simultaneously predict the semantic label and the temporal interval of every action instance in an untrimmed video. Rather than…

Computer Vision and Pattern Recognition · Computer Science 2022-04-07 Xiaolong Liu , Song Bai , Xiang Bai

We formulate a uniform tail bound for empirical processes indexed by a class of functions, in terms of the individual deviations of the functions rather than the worst-case deviation in the considered class. The tail bound is established by…

Probability · Mathematics 2026-03-27 Sohail Bahmani

This paper establishes a rigorous connection between regularized discrete-time reinforcement learning (RL) and continuous-time stochastic optimal control. Specifically, classical RL algorithms are typically solving a regularized…

Optimization and Control · Mathematics 2026-04-24 Huyên Pham , Yuming Paul Zhang , Yuhua Zhu

The primary goal of reinforcement learning is to develop decision-making policies that prioritize optimal performance, frequently without considering safety. In contrast, safe reinforcement learning seeks to reduce or avoid unsafe behavior.…

Machine Learning · Computer Science 2025-06-17 Zahra Shahrooei , Ali Baheri

We consider the emphatic temporal-difference (TD) algorithm, ETD($\lambda$), for learning the value functions of stationary policies in a discounted, finite state and action Markov decision process. The ETD($\lambda$) algorithm was recently…

Machine Learning · Computer Science 2017-01-23 Huizhen Yu

We study convex optimization problems under differential privacy (DP). With heavy-tailed gradients, existing works achieve suboptimal rates. The main obstacle is that existing gradient estimators have suboptimal tail properties, resulting…

Machine Learning · Computer Science 2024-08-20 Puning Zhao , Jiafei Wu , Zhe Liu , Chong Wang , Rongfei Fan , Qingming Li

The goal of this paper is to investigate distributed temporal difference (TD) learning for a networked multi-agent Markov decision process. The proposed approach is based on distributed optimization algorithms, which can be interpreted as…

Machine Learning · Computer Science 2025-05-14 Han-Dong Lim , Donghwan Lee

This paper is concerned with the problem of policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes. We investigate the sample complexities required to guarantee a predefined estimation…

Machine Learning · Statistics 2024-05-03 Gen Li , Weichen Wu , Yuejie Chi , Cong Ma , Alessandro Rinaldo , Yuting Wei

We present tools for the analysis of Follow-The-Regularized-Leader (FTRL), Dual Averaging, and Mirror Descent algorithms when the regularizer (equivalently, prox-function or learning rate schedule) is chosen adaptively based on the data.…

Machine Learning · Computer Science 2015-11-10 H. Brendan McMahan

Distributional reinforcement learning (DRL) has achieved empirical success in various domains. One core task in DRL is distributional policy evaluation, which involves estimating the return distribution $\eta^\pi$ for a given policy $\pi$.…

Machine Learning · Statistics 2025-01-17 Yang Peng , Liangyu Zhang , Zhihua Zhang

We study realizable continual linear regression under random task orderings, a common setting for developing continual learning theory. In this setup, the worst-case expected loss after $k$ learning iterations admits a lower bound of…

Machine Learning · Computer Science 2025-10-28 Ran Levinstein , Amit Attia , Matan Schliserman , Uri Sherman , Tomer Koren , Daniel Soudry , Itay Evron