Discounted semi-markov decision process in a semi-markov environment

DOI10.1080/02331939708844291zbMATH Open0871.90104OpenAlexW1967471769MaRDI QIDQ4340164FDOQ4340164

Authors: Qiying Hu 

Publication date: 5 October 1997

Published in: Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02331939708844291

Recommendations

• The Borel state space semi-Markov decision process with expected total rewards in a semi-Markov environment
• Mixed Markov decision processes in a semi-Markov environment with discounted criterion
• Continuous time discounted markov decision process in a semi-markov environment with its approximating problem

zbMATH Keywords

existence of \(\varepsilon\)-optimal policiesdiscounted semi-Markov decision process

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cites Work

• Universally Measurable Policies in Dynamic Programming
• Markov programming by successive approximations with respect to weighted supremum norms
• Continuous time discounted markov decision process in a semi-markov environment with its approximating problem

Cited In (11)

• The Borel state space semi-Markov decision process with expected total rewards in a semi-Markov environment
• A survey on semi-Markov decision processes
• Discrete type shock semi-markov decision processes with borel state space
• Mixed Markov decision processes in a semi-Markov environment with discounted criterion
• A sojourn-based approach to semi-Markov reinforcement learning
• Performance optimization for countable semi-Markov decision processes with discounted-cost
• Optimality of quasi-open-loop policies for discounted semi-Markov decision processes
• Title not available (Why is that?)
• Continuous time discounted markov decision process in a semi-markov environment with its approximating problem
• Semi-Markov decision processes with a reachable state-subset
• Performance optimization of semi-Markov decision processes with discounted-cost criteria

This page was built for publication: Discounted semi-markov decision process in a semi-markov environment

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4340164)