Two-time scale reinforcement learning and applications to production planning

DOI10.1049/iet-cta.2020.0049zbMATH Open1542.93277MaRDI QIDQ6611543

L. Y. Wang, G. Yin, Unnamed Author

Publication date: 26 September 2024

Published in: IET Control Theory \& Applications (Search for Journal in Brave)

zbMATH Keywords

Monte Carlo methodsproduction planningaggregation processproduction planning problemaggregate stateslearning (artificial intelligence)two-time scale approximationstwo-time scale methodstwo-time scale reinforcement learning method

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Time-scale analysis and singular perturbations in control/observation systems (93C70)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Continuous-time Markov chains and applications. A two-time-scale approach
• A globally consistent nonlinear least squares estimator for identification of nonlinear rational systems
• Q-learning algorithms with random truncation bounds and applications to effective parallel computing
• Singular perturbation methods for ordinary differential equations
• Optimal control theory
• Asynchronous stochastic approximation and Q-learning
• On asymptotic properties of hyperparameter estimators for kernel-based regularization methods
• \({\mathcal Q}\)-learning
• Average Continuous Control of Piecewise Deterministic Markov Processes
• Perturbed Dynamical Systems with an Attracting Singularity and Weak Viscosity Limits in Hamilton-Jacobi Equations
• Optimality of an $(s, S)$ Policy with Compound Poisson and Diffusion Demands: A Quasi-variational Inequalities Approach
• Optimal control of production rate in a failure prone manufacturing system
• A singular perturbation approach to modeling and control of Markov chains
• On nearly optimal controls of hybrid LQG problems
• Solving high-dimensional partial differential equations using deep learning
• Variable selection in nonlinear non-parametric system\\ identification
• A Near-Optimal Selling Rule for a Two-Time-Scale Market Model
• Aggregation of Variables in Dynamic Systems
• Identification for Wiener-Hammerstein systems under quantized inputs and quantized output observations

This page was built for publication: Two-time scale reinforcement learning and applications to production planning