STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS*
From MaRDI portal
Publication:2710472
DOI10.1081/SAP-100001186zbMath0968.93082OpenAlexW2034323937MaRDI QIDQ2710472
Peng Shi, Xianping Guo, Wei-Ping Zhu
Publication date: 2 September 2001
Published in: Stochastic Analysis and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1081/sap-100001186
optimality equationsunbounded rewardsnon-homogeneous controlled Markov chain with denumerable state spacestrong average \(epsilon\)-optimal policystrong average criterion
Related Items
A risk minimization problem for finite horizon semi-Markov decision processes with loss rates, Average optimality for Markov decision processes in borel spaces: a new condition and approach
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Denumerable state nonhomogeneous Markov decision processes
- Markov decision processes with a minimum-variance criterion
- An expected average reward criterion
- On asymptotic optimization of a class of nonlinear stochastic hybrid systems
- Finite state Markov decision models with average reward criteria
- Optimal average value convergence in nonhomogeneous Markov decision processes
- Adaptive Markov control processes
- Finite state Markovian decision processes
- Value iteration in a class of average controlled Markov chains with unbounded costs: necessary and sufficient conditions for pointwise convergence
- Multichain Markov Decision Processes with a Sample Path Constraint: A Decomposition Approach
- Markov Decision Processes with a Borel Measurable Cost Function—The Average Case
- A New Optimality Criterion for Nonhomogeneous Markov Decision Processes
- Rolling Horizon Procedures in Nonhomogeneous Markov Decision Processes
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Markov Decision Processes with Sample Path Constraints: The Communicating Case
- Percentile performance criteria for limiting average Markov decision processes
- Discrete Dynamic Programming