Title | ||
---|---|---|
Finite approximation of the first passage models for discrete-time Markov decision processes with varying discount factors |
Abstract | ||
---|---|---|
This paper deals with the finite approximation of the first passage models for discrete-time Markov decision processes with varying discount factors. For a given control model ¿$\\mathcal {M}$ with denumerable states and compact Borel action sets, and possibly unbounded reward functions, under reasonable conditions we prove that there exists a sequence of control models ¿n$\\mathcal {M}_{n}$ such that the first passage optimal rewards and policies of ¿n$\\mathcal {M}_{n}$ converge to those of ¿$\\mathcal {M}$, respectively. Based on the convergence theorems, we propose a finite-state and finite-action truncation method for the given control model ¿$\\mathcal {M}$, and show that the first passage optimal reward and policies of ¿$\\mathcal {M}$ can be approximated by those of the solvable truncated finite control models. Finally, we give the corresponding value and policy iteration algorithms to solve the finite approximation models. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/s10626-014-0209-3 | Discrete Event Dynamic Systems |
Keywords | Field | DocType |
Discrete-time Markov decision processes,Finite approximation,First passage optimality,Varying discount factors | Convergence (routing),Discrete mathematics,Mathematical optimization,Countable set,Existential quantification,Markov decision process,Discrete time and continuous time,Truncation method,Mathematics | Journal |
Volume | Issue | ISSN |
26 | 4 | 0924-6703 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Xiao Wu | 1 | 11 | 3.75 |
Junyu Zhang | 2 | 0 | 0.34 |