Identification of optimal policies in Markov decision processes

MaRDI QIDQ3585656zbMATH OpenFDO

Authors Karel Sladký

Publication date 20 August 2010

Full work available at URL https://eudml.org/doc/196935, http://www.kybernetika.cz/content/2010/3/558

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)

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

Cites work

• scientific article; zbMATH DE number 5685899 (Why is no real title available?)
• A modified dynamic programming method for Markovian decision problems
• Action Elimination Procedures for Modified Policy Iteration Algorithms
• Dynamic programming, Markov chains, and the method of successive approximations
• Erratum—Tests for Suboptimal Actions in Discounted Markov Programming
• Letter to the Editor—A Test for Suboptimal Actions in Markovian Decision Problems
• Modified Policy Iteration Algorithms for Discounted Markov Decision Problems
• Note—A Test for Nonoptimal Actions in Undiscounted Finite Markov Decision Chains
• On Finding the Maximal Gain for Markov Decision Processes
• Pointwise approximations of discounted Markov decision processes to optimal policies
• Technical Note—Bounds on the Gain of a Markov Decision Process
• Technical Note—Elimination of Suboptimal Actions in Markov Decision Problems
• Uniform convergence of value iteration policies for discounted Markov decision processes

Cited in

(4)

• 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
• Reducing the number of queries in interactive value iteration

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)