A switching control strategy for policy selection in stochastic dynamic programming problems

DOI10.1016/J.AUTOMATICA.2024.111884MaRDI QIDQ6659170zbMATH OpenFDO

Authors Massimo Tipaldi, Raffaele Iervolino, David Naso

Publication date 8 January 2025

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.AUTOMATICA.2024.111884

zbMATH Keywords

Bellman operatordynamic programmingLyapunov functionstationary stochastic policiesswitched affine systems

Mathematics Subject Classification ID

Systems theory; control (93-XX)

Recommendations

• Algorithms for optimal control of stochastic switching systems
• A Lyapunov-based version of the value iteration algorithm formulated as a discrete-time switched affine system
• Temporal difference-based policy iteration for optimal control of stochastic systems
• Approximation of the infinite-horizon value function of the switched LQR problem
• Stochastic control via direct comparison

Cites work

• A convex optimization approach to synthesizing state feedback data-driven controllers for switched linear systems
• A Lyapunov-based version of the value iteration algorithm formulated as a discrete-time switched affine system
• Bounding fixed points of set-based Bellman operator and Nash equilibria of stochastic games
• Challenges of real-world reinforcement learning: definitions, benchmarks and analysis
• Data-driven optimal control with a relaxed linear program
• Dynamic programming and optimal control. Vol. 2
• scientific article; zbMATH DE number 2107836 (Why is no real title available?)
• Linear Matrix Inequalities in System and Control Theory
• Novel Practical Stability Conditions for Discrete-Time Switched Affine Systems
• On practical asymptotic stabilizability of switched affine systems
• Online learning of data-driven controllers for unknown switched linear systems
• Reinforcement learning. An introduction
• Stability Analysis and Control Design of Discrete-Time Switched Affine Systems
• Stability and Stabilizability of Switched Linear Systems: A Survey of Recent Results
• Temporal Difference Methods for General Projected Equations
• Transmission scheduling for multi-process multi-sensor remote estimation via approximate dynamic programming

Cited in

(1)

• A data-driven practical stabilization approach for solving stochastic dynamic programming problems

This page was built for publication: A switching control strategy for policy selection in stochastic dynamic programming problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6659170)