Optimal control for unknown mean-field discrete-time system based on Q-learning
From MaRDI portal
Publication:5029154
DOI10.1080/00207721.2021.1929554zbMATH Open1483.93704OpenAlexW3165186735MaRDI QIDQ5029154FDOQ5029154
Authors:
Publication date: 11 February 2022
Published in: International Journal of Systems Science. Principles and Applications of Systems and Integration (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/00207721.2021.1929554
Recommendations
- Finite-time stochastic linear quadratic optimal control based on \(Q\)-learning
- Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
- Finite-horizon optimal control of discrete-time linear systems with completely unknown dynamics using Q-learning
- A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
- Reinforcement \(Q\)-learning for optimal tracking control of linear discrete-time systems with unknown dynamics
Linear-quadratic optimal control problems (49N10) Discrete-time control/observation systems (93C55) Optimal stochastic control (93E20)
Cites Work
- Solvability and asymptotic behavior of generalized Riccati equations arising in indefinite stochastic LQ controls
- Mean field games and mean field type control theory
- On a Matrix Riccati Equation of Stochastic Control
- Discrete time mean-field stochastic linear-quadratic optimal control problems
- Indefinite Mean-Field Stochastic Linear-Quadratic Optimal Control
- Discrete-time mean-field stochastic linear-quadratic optimal control problems. II: Infinite horizon case
- Reinforcement Learning and Feedback Control: Using Natural Decision Methods to Design Optimal Adaptive Controllers
- Linear matrix inequalities, Riccati equations, and indefinite stochastic linear quadratic controls
- Indefinite Stochastic Linear Quadratic Control and Generalized Differential Riccati Equation
- Stochastic linear quadratic optimal control with constraint for discrete-time systems
- Reinforcement learning for adaptive optimal control of continuous-time linear periodic systems
- Stochastic linear quadratic optimal control problems
- Integral \(Q\)-learning and explorized policy iteration for adaptive optimal control of continuous-time linear systems
- On observability and detectability of continuous-time stochastic Markov jump systems
- Q-learning for continuous-time linear systems: A model-free infinite horizon optimal control approach
- Data-driven approximate Q-learning stabilization with optimality error bound analysis
- Adaptive Dynamic Programming for Stochastic Systems With State and Control Dependent Noise
- A Linear-Quadratic Optimal Control Problem of Forward-Backward Stochastic Differential Equations With Partial Information
- Moving Horizon Estimation With Unknown Inputs Under Dynamic Quantization Effects
- Moving horizon estimation with multirate measurements and correlated noises
- Optimal Stabilization Control for Discrete-Time Mean-Field Stochastic Systems
- Leader-follower stochastic differential game with asymmetric information and applications
- An optimal control problem for mean-field forward-backward stochastic differential equation with noisy observation
- Modeling and computation of mean field equilibria in producers' game with emission permits trading
- An integral control formulation of mean field game based large scale coordination of loads in smart grids
- Optimal Robust Linear Quadratic Regulator for Systems Subject to Uncertainties
- Dynamic event-triggered mechanism for \(H_\infty\) non-fragile state estimation of complex networks under randomly occurring sensor saturations
- A Mean-Field Optimal Control Formulation for Global Optimization
- Moving horizon estimation with non-uniform sampling under component-based dynamic event-triggered transmission
- \(\mathcal{H}_-\) index for continuous-time stochastic systems with Markov jump and multiplicative noise
Cited In (11)
- Finite-horizon optimal control of discrete-time linear systems with completely unknown dynamics using Q-learning
- Controlled interacting particle algorithms for simulation-based reinforcement learning
- An adaptive dynamic programming-based algorithm for infinite-horizon linear quadratic stochastic optimal control problems
- State-flipped control and Q-learning for finite horizon output tracking of Boolean control networks
- Finite-time stochastic linear quadratic optimal control based on \(Q\)-learning
- Kullback–Leibler-Quadratic Optimal Control
- Unified reinforcement Q-learning for mean field game and control problems
- Two‐loop reinforcement learning algorithm for finite‐horizon optimal control of continuous‐time affine nonlinear systems
- A Q-Learning Algorithm for Discrete-Time Linear-Quadratic Control with Random Parameters of Unknown Distribution: Convergence and Stabilization
- Continuous time q-learning for mean-field control problems
- Mean field LQG social optimization: a reinforcement learning approach
This page was built for publication: Optimal control for unknown mean-field discrete-time system based on Q-learning
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5029154)
