Asymptotic properties of constrained Markov Decision Processes
From MaRDI portal
Publication:5286754
DOI10.1007/BF01414154zbMath0799.90118MaRDI QIDQ5286754
Publication date: 17 November 1994
Published in: ZOR - Methods and Models of Operations Research (Search for Journal in Brave)
Deterministic scheduling theory in operations research (90B35) Markov and semi-Markov decision processes (90C40)
Related Items
Constrained Semi-Markov decision processes with average rewards ⋮ On the Taylor Expansion of Value Functions ⋮ SEMI-MARKOV DECISION PROCESSES ⋮ Constrained denumerable state non-stationary MDPs with expected total reward criterion
Cites Work
- Unnamed Item
- Unnamed Item
- Finite state approximations for denumerable state infinite horizon discounted Markov decision processes with unbounded rewards
- K competing queues with geometric service requirements and linear costs: The \(\mu\) c-rule is always optimal
- Finite state approximation algorithms for average cost denumerable state Markov decision processes
- Optimal policies for controlled Markov chains with a constraint
- Finite-state approximations for denumerable multidimensional state discounted Markov decision processes
- Scanning control of a vibrating string
- Sensitivity of constrained Markov decision processes
- Optimal priority assignment with hard constraint
- Optimal flow control of a class of queueing networks in equilibrium
- Markov Decision Problems and State-Action Frequencies
- Constrained Discounted Markov Decision Chains
- Optimal priority assignment: a time sharing approach
- Constrained Undiscounted Stochastic Dynamic Programming
- Average, Sensitive and Blackwell Optimal Policies in Denumerable Markov Decision Chains with Unbounded Rewards
- Constrained admission control to a queueing system
- Adaptive control of constrained Markov chains
- Sensitive Optimality Criteria in Countable State Dynamic Programming
- Denumerable Constrained Markov Decision Processes and Finite Approximations
