Stochastic approximation. A dynamical systems viewpoint.

DOI10.1007/978-93-86279-38-5zbMath1159.60002OpenAlexW4243772471MaRDI QIDQ1013655

Publication date: 20 April 2009

Published in: Texts and Readings in Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/978-93-86279-38-5

Mathematics Subject Classification ID

Research exposition (monographs, survey articles) pertaining to dynamical systems and ergodic theory (37-02) Research exposition (monographs, survey articles) pertaining to probability theory (60-02)

Related Items

Approximate policy iteration: a survey and some new methods, Stochastic approximation method using diagonal positive-definite matrices for convex optimization with fixed point constraints, Asynchronous stochastic approximation with differential inclusions, A Stochastic Approximation Method for Simulation-Based Quantile Optimization, Distributed resource allocation over random networks based on stochastic approximation, Approximate consensus in the dynamic stochastic network with incomplete information and measurement delays, Distributed dynamic reinforcement of efficient outcomes in multiagent coordination and network formation, Sparse optimal control problems with intermediate constraints: Necessary conditions, Risk-Sensitive Reinforcement Learning via Policy Gradient Search, Variance-constrained actor-critic algorithms for discounted and average reward MDPs, Diffusion of binary opinions in a growing population with heterogeneous behaviour and external influence, Stochastic heavy ball, A Concentration Bound for Stochastic Approximation via Alekseev’s Formula, Independent learning in stochastic games, Asymptotic bias of stochastic gradient search, Local voting protocol for decentralized load balancing of network with switched topology and noise in measurements, Global Convergence of Policy Gradient Methods to (Almost) Locally Optimal Policies, Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions, Is Temporal Difference Learning Optimal? An Instance-Dependent Analysis, Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization, Improving control performance across AWGN channels using a relay node^†, Central limit theorems for stochastic approximation with controlled Markov chain dynamics, Opportunistic Transmission over Randomly Varying Channels, Multi-armed bandits based on a variant of simulated annealing, Event-driven stochastic approximation, Langevin type limiting processes for adaptive MCMC, Continuous monitoring for changepoints in data streams using adaptive estimation, Simultaneous Perturbation Stochastic Approximation with Norm-Limited Update Vector, Concentration bounds for temporal difference learning with linear function approximation: the case of batch data and uniform sampling, Robust scheduling for flexible processing networks, Revisiting the ODE method for recursive algorithms: fast convergence using quasi stochastic approximation, An ODE method to prove the geometric convergence of adaptive stochastic algorithms, Multi-agent consensus under a communication–broadcast mixed environment, Stochastic approximation with random step sizes and urn models with random replacement matrices having finite mean, Fundamental design principles for reinforcement learning algorithms, Multi-agent reinforcement learning: a selective overview of theories and algorithms, Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation, Unnamed Item, Distributed Stochastic Optimization with Large Delays, Analyzing Approximate Value Iteration Algorithms, Actor-Critic Algorithms with Online Feature Adaptation, Smoothed Functional Algorithms for Stochastic Optimization Using q -Gaussian Distributions