A note on the convergence rate of the value iteration scheme in controlled Markov chains
From MaRDI portal
Publication:1128695
DOI10.1016/S0167-6911(97)00097-2zbMath0902.93070OpenAlexW1982510099MaRDI QIDQ1128695
Publication date: 13 August 1998
Published in: Systems \& Control Letters (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/s0167-6911(97)00097-2
Markov decision processesgeometric convergence ratelong-run average cost criterionsimultaneous Doeblin condition
Related Items (3)
Open Problem—Convergence and Asymptotic Optimality of the Relative Value Iteration in Ergodic Control ⋮ Asymptotic behavior of the value functions of discrete-time discounted optimal control ⋮ Successive approximations in partially observable controlled Markov chains with risk-sensitive average criterion
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Value iteration in countable state average cost Markov decision processes with unbounded costs
- Necessary and sufficient conditions for a bounded solution to the optimality equation in average reward Markov decision chains
- Adaptive Markov control processes
- Dynamic programming, Markov chains, and the method of successive approximations
- Iterative solution of the functional equations of undiscounted Markov renewal programming
- Value iteration in a class of average controlled Markov chains with unbounded costs: necessary and sufficient conditions for pointwise convergence
- On Minimum Cost Per Unit Time Control of Markov Chains
- Value Iteration in a Class of Communicating Markov Decision Chains with the Average Cost Criterion
- The asymptotic behaviour of the minimal total expected cost for the denumerable state Markov decision model
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
This page was built for publication: A note on the convergence rate of the value iteration scheme in controlled Markov chains
