Error bounds of optimization algorithms for semi-Markov decision processes

DOI10.1080/00207720701596656MaRDI QIDQ3625261zbMATH OpenOpenAlexFDO

Authors Tang Hao, Yin Baoqun, Xi Hongsheng

Publication date 12 May 2009

Published in International Journal of Systems Science. Principles and Applications of Systems and Integration (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/00207720701596656

zbMATH Keywords

error boundperformance potentialsemi-Markov decision processesuniformized Markov chain

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40) Discrete event control/observation systems (93C65) Stochastic systems in control theory (general) (93E03)

Recommendations

• Performance optimization of semi-Markov decision processes with discounted-cost criteria
• Performance optimization algorithms based on potentials for semi-Markov control processes
• Performance optimization for countable semi-Markov decision processes with discounted-cost
• scientific article; zbMATH DE number 3871063
• Error bounds for stochastic shortest path problems

Cites work

• A unified approach to Markov decision problems and performance sensitivity analysis
• CSPS model: Look-ahead controls and physics
• From perturbation analysis to Markov decision processes and reinforcement learning
• Fuzzy modelling and simulation for aggregate production planning
• Perturbation realization, potentials, and sensitivity analysis of Markov processes
• Semi-markov decision problems and performance sensitivity analysis
• Single sample path-based sensitivity analysis of Markov processes using uniformization
• Successive approximation approach of optimal control for nonlinear discrete-time systems
• The relations among potentials, perturbation analysis, and Markov decision processes

Cited in

(2)

• Coupling based estimation approaches for the average reward performance potential in Markov chains
• Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration

This page was built for publication: Error bounds of optimization algorithms for semi-Markov decision processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3625261)