Constrained denumerable state non-stationary MDPs with expected total reward criterion
From MaRDI portal
Publication:1568256
DOI10.1007/BF02677681zbMath0971.90102MaRDI QIDQ1568256
Publication date: 21 June 2000
Published in: Acta Mathematicae Applicatae Sinica. English Series (Search for Journal in Brave)
non-stationary Markov decision processes; expected total reward criterion; Markov policy; constrained optimal policies
90C40: Markov and semi-Markov decision processes
Related Items
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- On discounted dynamic programming with constraints
- Optimal policies for controlled Markov chains with a constraint
- Finite state Markovian decision processes
- Markov Decision Problems and State-Action Frequencies
- Constrained Discounted Markov Decision Chains
- Constrained Undiscounted Stochastic Dynamic Programming
- Controlled Markov processes on the infinite planning horizon: Weighted and overtaking cost criteria
- Asymptotic properties of constrained Markov Decision Processes