Suboptimal policy determination for large-scale Markov decision processes. I: Description and bounds

DOI10.1007/BF00939287zbMATH Open0548.90084MaRDI QIDQ799497FDOQ799497

Authors: Chelsea C. White, J. L. Popyack 

Publication date: 1985

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

Recommendations

• Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation
• Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation
• Suboptimal Policies, with Bounds, for Parameter Adaptive Decision Processes
• Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
• On Finding Optimal Policies for Markov Decision Chains: A Unifying Framework for Mean-Variance-Tradeoffs
• Policy Bounds for Markov Decision Processes
• Suboptimal Policies for Stochastic $$N$$-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption
• Approximation of average cost optimal policies for general Markov decision processes with unbounded costs
• Estimate and approximate policy iteration algorithm for discounted Markov decision models with bounded costs and Borel spaces

zbMATH Keywords

finite state and action spacessuboptimal policiesinfinite-horizon expected total discounted costlarge-scale Markov decision processes

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Dynamic programming and stochastic control
• Approximations of Dynamic Programs, I
• Quality Control under Markovian Deterioration
• A survey of maintenance models: The control and surveillance of deteriorating systems
• Convex composite multi-objective nonsmooth programming
• Title not available (Why is that?)
• Approximations of Dynamic Programs, II
• An Iterative Aggregation Procedure for Markov Decision Processes
• Title not available (Why is that?)
• Suboptimal Design for Large Scale, Multimodule Systems
• Applications of dynamic programming and other optimization methods in pest management
• Optimal Integrated Control of Univoltine Pest Populations with Age Structure
• Multilayer control of large Markov chains

Cited In (10)

• A methodology for computation reduction for specially structured large scale Markov decision problems
• Reward revision and the average reward Markov decision process
• Suboptimal solutions to dynamic optimization problems via approximations of the policy functions
• Suboptimal Policies for Stochastic $$N$$-Stage Optimization: Accuracy Analysis and a Case Study from Optimal Consumption
• Identification of optimal policies in Markov decision processes
• New approximate dynamic programming algorithms for large-scale undiscounted Markov decision processes and their application to optimize a production and distribution system
• Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation
• Suboptimal policy determination for large-scale Markov decision processes. II: Implementation and numerical evaluation
• Policy Bounds for Markov Decision Processes
• Markov decision processes

This page was built for publication: Suboptimal policy determination for large-scale Markov decision processes. I: Description and bounds

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q799497)