A note on generalized second-order value iteration in Markov decision processes

DOI10.1007/s10957-023-02309-xMaRDI QIDQ6145054

Villavarayan Antony Vijesh, Mohammed Shahid Abdulla, Shreyas Sumithra Rudresha

Publication date: 8 January 2024

Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)

zbMATH Keywords

Markov decision processesreinforcement learningvalue iterationQ-learning

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Value iteration and adaptive dynamic programming for data-driven adaptive optimal control design
• Fixed point theorems in ordered Banach spaces via quasilinearization
• \({\mathcal Q}\)-learning
• Block monotone iterative methods for numerical solutions of nonlinear elliptic equations
• On the Convergence of Policy Iteration in Stationary Dynamic Programming
• Convergence Properties of Policy Iteration
• Iterative Solution of Nonlinear Equations in Several Variables
• Generalized Second-Order Value Iteration in Markov Decision Processes
• Accurately computing the log-sum-exp and softmax functions
• Bias-Corrected Q-Learning With Multistate Extension
• A Unified Convergence Theory for a Class of Iterative Processes
• Newton’s Method for Convex Operators in Partially Ordered Spaces
• Monotone Iterations for Nonlinear Equations with Application to Gauss-Seidel Methods
• Global Convergence of Newton–Gauss–Seidel Methods
• Solution of a Markovian decision problem by successive overrelaxation
• A Generalized Minimax Q-Learning Algorithm for Two-Player Zero-Sum Stochastic Games
• A First-Order Approach to Accelerated Value Iteration

This page was built for publication: A note on generalized second-order value iteration in Markov decision processes