Results 1 to 10 of about 49 (34)
Asynchronous stochastic approximation with differential inclusions [PDF]
Stochastic Systems, 2012 The asymptotic pseudo-trajectory approach to stochastic approximation of Benaïm, Hofbauer and Sorin is extended for asynchronous stochastic approximations with a set-valued mean field.
David S. Leslie, Steven Perkins
doaj +10 more sources
Asynchronous Stochastic Approximations [PDF]
SIAM Journal on Control and Optimization, 1998 The asymptotic behavior of a distributed, asynchronous stochastic approximation scheme is analyzed in terms of a limiting nonautonomous differential equation. The relation between the latter and the relative values of suitably rescaled relative frequencies of updates of different components is underscored.
Vivek Borkar
exaly +4 more sources
Practical Precoding via Asynchronous Stochastic Successive Convex Approximation [PDF]
IEEE Transactions on Signal Processing, 2021 We consider stochastic optimization of a smooth non-convex loss function with a convex non-smooth regularizer. In the online setting, where a single sample of the stochastic gradient of the loss is available at every iteration, the problem can be solved using the proximal stochastic gradient descent (SGD) algorithm and its variants.
Basil M Idrees +2 more
exaly +5 more sources
Asynchronous Stochastic Approximations With Asymptotically Biased Errors and Deep Multiagent Learning [PDF]
IEEE Transactions on Automatic Control, 2021 Asynchronous stochastic approximations (SAs) are an important class of model-free algorithms, tools, and techniques that are popular in multiagent and distributed control scenarios. To counter Bellman's curse of dimensionality, such algorithms are coupled with function approximations.
Arunselvan Ramaswamy +2 more
exaly +4 more sources
Asynchronous Stochastic Approximation and Q-Learning [PDF]
Machine Learning, 1994 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
exaly +7 more sources
Asynchronous Stochastic Approximation With Applications to Average-Reward Reinforcement Learning
SIAM Journal on Control and OptimizationAbstract. This paper investigates the stability and convergence properties of asynchronous stochastic approximation (SA) algorithms, with a focus on extensions relevant to average-reward reinforcement learning. We first extend a stability proof method of Borkar and Meyn to accommodate more general noise conditions than previously ...
Huizhen Yu, Richard S. Sutton
exaly +3 more sources
Complexity, 2021 This study focuses on the static output feedback control of nonlinear Markov jump singularly perturbed systems within the framework of Takagi–Sugeno fuzzy approximation. From a practical point of view, the phenomenon of asynchronous switching between the
Baogang Ding +3 more
doaj +1 more source
CoRR, 2021 We begin by briefly surveying some results on the convergence of the Stochastic Gradient Descent (SGD) Method, proved in a companion paper by the present authors. These results are based on viewing SGD as a version of Stochastic Approximation (SA). Ever since its introduction in the classic paper of Robbins and Monro in 1951, SA has become a standard ...
Rajeeva Laxman Karandikar, M. Vidyasagar
openaire +3 more sources
A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays
CoRR, 2023 In this paper, we study asynchronous stochastic approximation algorithms without communication delays. Our main contribution is a stability proof for these algorithms that extends a method of Borkar and Meyn by accommodating more general noise conditions.
Huizhen Yu +2 more
openaire +3 more sources
Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning
CoRR, 2020 We consider a general asynchronous Stochastic Approximation (SA) scheme featuring a weighted infinity-norm contractive operator, and prove a bound on its finite-time convergence rate on a single trajectory.
Qu, Guannan, Wierman, Adam
openaire +5 more sources