Asynchronous Stochastic Approximations

DOI10.1137/S0363012995282784MaRDI QIDQ4388937zbMATH OpenOpenAlexFDO

Authors Vivek Borkar

Publication date 10 May 1998

Published in SIAM Journal on Control and Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/s0363012995282784

zbMATH Keywords

communicationdistributed algorithmsdelaysasynchronous algorithmsapproximation ODE limit

Mathematics Subject Classification ID

Stochastic approximation (62L20) Numerical methods for ordinary differential equations (65L99)

Recommendations

• Asymptotic behavior of asynchronous stochastic approximation
• Asynchronous stochastic approximation with differential inclusions
• The Borkar-Meyn theorem for asynchronous stochastic approximations
• Distributed asynchronous deterministic and stochastic gradient optimization algorithms

Cited in

(29)

• scientific article; zbMATH DE number 1788242 (Why is no real title available?)
• Fully asynchronous stochastic coordinate descent: a tight lower bound on the parallelism achieving linear speedup
• A note on the effect of asynchronous sampling on estimation accuracy
• The Borkar-Meyn theorem for asynchronous stochastic approximations
• Convergence rates for stochastic approximation: biased noise with unbounded variance, and applications
• Whittle index based Q-learning for restless bandits with average reward
• Q-learning for Markov decision processes with a satisfiability criterion
• Asymptotics of Reinforcement Learning with Neural Networks
• Stochastic fictitious play with continuous action sets
• Asymptotic behavior of asynchronous stochastic approximation
• Iterative learning control for large scale nonlinear systems with observation noise
• Partially asynchronous co-state prediction algorithm
• Nonlinear gossip
• Asynchronous stochastic approximation with differential inclusions
• A stochastic gradient type algorithm for closed-loop problems
• An online actor-critic algorithm with function approximation for constrained Markov decision processes
• Asymptotic agreement and convergence of asynchronous stochastic algorithms
• A sensitivity formula for risk-sensitive cost and the actor-critic algorithm
• Random asynchronous iterations in distributed coordination algorithms
• Approachability in Stackelberg stochastic games with vector costs
• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• Charge-based control of DiffServ-like queues
• Reinforcement learning for long-run average cost.
• Distributed time synchronization for networks with random delays and measurement noise
• Stochastic approximation algorithms: overview and recent trends.
• Event-driven stochastic approximation
• Convergence analysis of contrastive divergence algorithm based on gradient method with errors
• Reinforcement learning based algorithms for average cost Markov decision processes
• Current fluctuations of a self-interacting diffusion on a ring

This page was built for publication: Asynchronous Stochastic Approximations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4388937)