English
Related papers

Related papers: Concentration of Contractive Stochastic Approximat…

200 papers

We introduce a class of Markov chains, that contains the model of stochastic approximation by averaging and non-averaging. Using martingale approximation method, we establish various deviation inequalities for separately Lipschitz functions…

Probability · Mathematics 2022-09-16 Xiequan Fan , Pierre Alquier , Paul Doukhan

We investigate the problem of learning the structure of a Markov network from data. It is shown that the structure of such networks can be described in terms of constraints which enables the use of existing solver technology with…

Artificial Intelligence · Computer Science 2013-10-04 Jukka Corander , Tomi Janhunen , Jussi Rintanen , Henrik Nyman , Johan Pensar

This paper gives specific divergence examples of value-iteration for several major Reinforcement Learning and Adaptive Dynamic Programming algorithms, when using a function approximator for the value function. These divergence examples…

Machine Learning · Computer Science 2012-07-31 Michael Fairbank , Eduardo Alonso

Many reinforcement learning algorithms are built on an assumption that an agent interacts with an environment over fixed-duration, discrete time steps. However, physical systems are continuous in time, requiring a choice of…

Machine Learning · Computer Science 2024-09-04 Kris De Asis , Richard S. Sutton

Catastrophic forgetting is of special importance in reinforcement learning, as the data distribution is generally non-stationary over time. We study and compare several pseudorehearsal approaches for Q-learning with function approximation…

Artificial Intelligence · Computer Science 2017-03-22 Vladimir Marochko , Leonard Johard , Manuel Mazzara

We discuss a variant of Thompson sampling for nonparametric reinforcement learning in a countable classes of general stochastic environments. These environments can be non-Markov, non-ergodic, and partially observable. We show that Thompson…

Machine Learning · Computer Science 2016-06-06 Jan Leike , Tor Lattimore , Laurent Orseau , Marcus Hutter

As a primary contribution, we present a convergence theorem for stochastic iterations, and in particular, Q-learning iterates, under a general, possibly non-Markovian, stochastic environment. Our conditions for convergence involve an…

Optimization and Control · Mathematics 2024-03-05 Ali Devran Kara , Serdar Yuksel

In the stochastic knapsack problem, we are given a knapsack of size B, and a set of jobs whose sizes and rewards are drawn from a known probability distribution. However, we know the actual size and reward only when the job completes. How…

Data Structures and Algorithms · Computer Science 2011-02-21 Anupam Gupta , Ravishankar Krishnaswamy , Marco Molinaro , R. Ravi

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

We give Hoeffding and Bernstein-type concentration inequalities for the largest eigenvalue of sums of random matrices arising from a Markov chain. We consider time-dependent matrix-valued functions on a general state space, generalizing…

Probability · Mathematics 2025-07-01 Joe Neeman , Bobby Shi , Rachel Ward

This work develops new results for stochastic approximation algorithms. The emphases are on treating algorithms and limits with discontinuities. The main ingredients include the use of differential inclusions, set-valued analysis, and…

Probability · Mathematics 2021-08-31 Nhu Nguyen , George Yin

We present on-line policy gradient algorithms for computing the locally optimal policy of a constrained, average cost, finite state Markov Decision Process. The stochastic approximation algorithms require estimation of the gradient of the…

Optimization and Control · Mathematics 2018-12-18 Vikram Krishnamurthy , Felisa Vazquez Abad

Although stochastic approximation learning methods have been widely used in the machine learning literature for over 50 years, formal theoretical analyses of specific machine learning algorithms are less common because stochastic…

Machine Learning · Statistics 2017-04-21 Richard M. Golden

This work presents the first finite-time analysis for the last-iterate convergence of average-reward $Q$-learning with an asynchronous implementation. A key feature of the algorithm we study is the use of adaptive stepsizes, which serve as…

Machine Learning · Computer Science 2026-04-07 Zaiwei Chen , Phalguni Nanda

Temporal-difference learning with gradient correction (TDC) is a two time-scale algorithm for policy evaluation in reinforcement learning. This algorithm was initially proposed with linear function approximation, and was later extended to…

Machine Learning · Computer Science 2021-10-29 Yue Wang , Shaofeng Zou , Yi Zhou

In reinforcement learning (RL), it is often advantageous to consider additional constraints on the action space to ensure safety or action relevance. Existing work on such action-constrained RL faces challenges regarding effective policy…

Machine Learning · Computer Science 2025-12-01 Roland Stolz , Michael Eichelbeck , Matthias Althoff

We investigate the finite-time convergence properties of Temporal Difference (TD) learning with linear function approximation, a cornerstone algorithm in the field of reinforcement learning. We are interested in the so-called ``robust''…

Machine Learning · Computer Science 2025-09-26 Wei-Cheng Lee , Francesco Orabona

We study the so-called two-time-scale stochastic approximation, a simulation-based approach for finding the roots of two coupled nonlinear operators. Our focus is to characterize its finite-time performance in a Markov setting, which often…

Optimization and Control · Mathematics 2021-04-06 Thinh T. Doan

Constraint handling plays a key role in solving realistic complex optimization problems. Though intensively discussed in the last few decades, existing constraint handling techniques predominantly rely on human experts' designs, which more…

Neural and Evolutionary Computing · Computer Science 2026-02-03 Qianhao Zhu , Sijie Ma , Zeyuan Ma , Hongshu Guo , Yue-Jiao Gong

One of the most basic problems in reinforcement learning (RL) is policy evaluation: estimating the long-term return, i.e., value function, corresponding to a given fixed policy. The celebrated Temporal Difference (TD) learning algorithm…

Machine Learning · Computer Science 2025-02-10 Sreejeet Maity , Aritra Mitra