Identification of optimal policies in Markov decision processes

zbMATH Open1195.93148MaRDI QIDQ3585656FDOQ3585656

Authors: Karel Sladký 

Publication date: 20 August 2010

Full work available at URL: https://eudml.org/doc/196935

Recommendations

• Adaptive policy-iteration and policy-value-iteration for discounted Markov decision processes
• Suboptimal policy determination for large-scale Markov decision processes. I: Description and bounds
• Uniform convergence of value iteration policies for discounted Markov decision processes
• scientific article; zbMATH DE number 522741
• Bounds for the quality and the number of steps in Bellman's value iteration algorithm

zbMATH Keywords

finite state Markov decision processesdiscounted and average costselimination of suboptimal policies

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20)

Cites Work

• Dynamic programming, Markov chains, and the method of successive approximations
• Title not available (Why is that?)
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Action Elimination Procedures for Modified Policy Iteration Algorithms
• On Finding the Maximal Gain for Markov Decision Processes
• A modified dynamic programming method for Markovian decision problems
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Technical Note—Bounds on the Gain of a Markov Decision Process
• Note—A Test for Nonoptimal Actions in Undiscounted Finite Markov Decision Chains
• Technical Note—Elimination of Suboptimal Actions in Markov Decision Problems
• Pointwise approximations of discounted Markov decision processes to optimal policies
• Uniform convergence of value iteration policies for discounted Markov decision processes
• Erratum—Tests for Suboptimal Actions in Discounted Markov Programming

Cited In (3)

• Detecting optimal and non-optimal actions in average-cost Markov decision processes
• Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation
• Policy space identification in configurable environments

This page was built for publication: Identification of optimal policies in Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3585656)