Uniform convergence of value iteration policies for discounted Markov decision processes

MaRDI QIDQ2467010zbMATH OpenFDO

Authors Daniel Cruz-Suárez, Raúl Montes-de-Oca

Publication date 18 January 2008

Published in Boletín de la Sociedad Matemática Mexicana. Third Series (Search for Journal in Brave)

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Recommendations

• The convergence of value iteration in discounted Markov decision processes
• On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case
• On convergence of value iteration for a class of total cost Markov decision processes
• Pointwise approximations of discounted Markov decision processes to optimal policies
• The value iteration method for countable state Markov decision processes

Cited in

(18)

• A Note on the Convergence of Policy Iteration in Markov Decision Processes with Compact Action Spaces
• Simulation‐based Uniform Value Function Estimates of Markov Decision Processes
• A mixed value and policy iteration method for stochastic control with universally measurable policies
• Convergence of value functions for finite horizon Markov decision processes with constraints
• Regular policies in abstract dynamic programming
• A stopping rule for discounted Markov decision processes with finite action sets
• Nonuniqueness versus uniqueness of optimal policies in convex discounted Markov decision processes
• Pointwise approximations of discounted Markov decision processes to optimal policies
• Identification of optimal policies in Markov decision processes
• An empirical study of policy convergence in Markov decision process value iteration
• On convergence of value iteration for a class of total cost Markov decision processes
• On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case
• Suboptimality of the value iteration policies in discounted linear-quadratic models
• The convergence of value iteration in discounted Markov decision processes
• A Lyapunov-based version of the value iteration algorithm formulated as a discrete-time switched affine system
• Convergence Properties of Policy Iteration
• scientific article; zbMATH DE number 790730 (Why is no real title available?)
• Convergence in unconstrained discrete-time differential dynamic programming

This page was built for publication: Uniform convergence of value iteration policies for discounted Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2467010)