Stochastic approximation with two time scales
From MaRDI portal
Publication:1391875
DOI10.1016/S0167-6911(97)90015-3zbMath0895.62085OpenAlexW2094364653MaRDI QIDQ1391875
Publication date: 23 July 1998
Published in: Systems \& Control Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/s0167-6911(97)90015-3
Time-scale analysis and singular perturbations in control/observation systems (93C70) Stochastic approximation (62L20)
Related Items (66)
A Biologically Plausible Neural Network for Multichannel Canonical Correlation Analysis ⋮ Recursive regression estimation based on the two-time-scale stochastic approximation method and Bernstein polynomials ⋮ A Two-Timescale Stochastic Algorithm Framework for Bilevel Optimization: Complexity Analysis and Application to Actor-Critic ⋮ Convergence rate of linear two-time-scale stochastic approximation. ⋮ Sequential online subsampling for thinning experimental designs ⋮ An online prediction algorithm for reinforcement learning with linear function approximation using cross entropy method ⋮ A new learning algorithm for optimal stopping ⋮ Multiscale Q-learning with linear function approximation ⋮ Asynchronous stochastic approximation with differential inclusions ⋮ A Stochastic Approximation Method for Simulation-Based Quantile Optimization ⋮ Online calibrated forecasts: memory efficiency versus universality for learning in games ⋮ Unified reinforcement Q-learning for mean field game and control problems ⋮ Convergence rate and averaging of nonlinear two-time-scale stochastic approximation algo\-rithms ⋮ Distributed Stochastic Approximation with Local Projections ⋮ A Diffusion Approximation Theory of Momentum Stochastic Gradient Descent in Nonconvex Optimization ⋮ A stability criterion for two timescale stochastic approximation schemes ⋮ Optimizing Adaptive Importance Sampling by Stochastic Approximation ⋮ Robustness Properties in Fictitious-Play-Type Algorithms ⋮ Risk-Sensitive Reinforcement Learning via Policy Gradient Search ⋮ Stochastic fictitious play with continuous action sets ⋮ Batching Adaptive Variance Reduction ⋮ Bayesian experimental design without posterior calculations: an adversarial approach ⋮ On the sample complexity of actor-critic method for reinforcement learning with function approximation ⋮ Geometrical Insights for Implicit Generative Modeling ⋮ Stochastic heavy ball ⋮ Two-time-scale nonparametric recursive regression estimator for independent functional data ⋮ Reinforcement learning algorithms with function approximation: recent advances and applications ⋮ Towards multi‐agent reinforcement learning‐driven over‐the‐counter market simulations ⋮ Two-timescale stochastic gradient descent in continuous time with applications to joint online parameter estimation and optimal sensor placement ⋮ Weak convergence of dynamical systems in two timescales ⋮ Monte-Carlo estimation of time-dependent statistical characteristics of random dynamical systems ⋮ New algorithms of the Q-learning type ⋮ Gradient-Based Adaptive Stochastic Search for Simulation Optimization Over Continuous Space ⋮ Reinforcement learning for long-run average cost. ⋮ Convergent multiple-timescales reinforcement learning algorithms in normal form games ⋮ Adaptive Monte Carlo variance reduction for Lévy processes with two-time-scale stochastic approximation ⋮ Stochastic Dynamic Information Flow Tracking Game with Reinforcement Learning ⋮ Non asymptotic controls on a recursive superquantile approximation ⋮ Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991) ⋮ Stochastic compositional gradient descent: algorithms for minimizing compositions of expected-value functions ⋮ Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach ⋮ Unnamed Item ⋮ Q-learning for Markov decision processes with a satisfiability criterion ⋮ Adaptive Monte Carlo Variance Reduction with Two-time-scale Stochastic Approximation ⋮ Adaptive importance sampling and control variates ⋮ Single-leader-multiple-follower games with boundedly rational agents ⋮ Two Timescale Analysis of the Alopex Algorithm for Optimization ⋮ Stochastic approximation on Riemannian manifolds ⋮ Linear stochastic approximation driven by slowly varying Markov chains ⋮ An actor-critic algorithm for constrained Markov decision processes ⋮ The actor-critic algorithm as multi-time-scale stochastic approximation. ⋮ Stochastic approximation algorithms: overview and recent trends. ⋮ REINFORCEMENT LEARNING IN MARKOVIAN EVOLUTIONARY GAMES ⋮ A sensitivity formula for risk-sensitive cost and the actor-critic algorithm ⋮ A two Timescale Stochastic Approximation Scheme for Simulation-Based Parametric Optimization ⋮ Simulation Optimization Using Multi-Time-Scale Adaptive Random Search ⋮ Stochastic approximation algorithms for superquantiles estimation ⋮ Nonlinear Gossip ⋮ Two Time-Scale Stochastic Approximation with Controlled Markov Noise and Off-Policy Temporal-Difference Learning ⋮ Stochastic Recursive Inclusions in Two Timescales with Nonadditive Iterate-Dependent Markov Noise ⋮ Generalization error of GAN from the discriminator's perspective ⋮ Computing VaR and CVaR using stochastic approximation and adaptive unconstrained importance sampling ⋮ Natural actor-critic algorithms ⋮ Joint Online Parameter Estimation and Optimal Sensor Placement for the Partially Observed Stochastic Advection-Diffusion Equation ⋮ Analyzing Approximate Value Iteration Algorithms ⋮ Actor-Critic Algorithms with Online Feature Adaptation
Cites Work
- Singular perturbations and asymptotic analysis in control systems
- Stochastic approximation methods for constrained and unconstrained systems
- Weak convergence methods and singularly perturbed stochastic control and filtering problems
- Asynchronous stochastic approximation and Q-learning
- A tutorial survey of reinforcement learning
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
This page was built for publication: Stochastic approximation with two time scales
