Finite state Markov decision models with average reward criteria
From MaRDI portal
Publication:1315409
DOI10.1016/0304-4149(94)90116-3zbMath0787.60085OpenAlexW2023957456MaRDI QIDQ1315409
Haechurl Park, Eugene A. Feinberg
Publication date: 19 May 1994
Published in: Stochastic Processes and their Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/0304-4149(94)90116-3
stationary strategiesaverage reward criteriadiscrete time Markov decision modelnearly optimal strategiesnon-repeating condition
Related Items (2)
STRONG AVERAGE OPTIMALITY FOR CONTROLLED NONHOMOGENEOUS MARKOV CHAINS* ⋮ The average cost of Markov chains subject to total variation distance uncertainty
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Existence of optimal stationary policies in deterministic optimal control
- On maximizing the average time at a goal
- The existence of good Markov strategies for decision processes with general payoffs
- Communicating MDPs: Equivalence and LP properties
- An expected average reward criterion
- Measurable sets of measures
- Finite state Markovian decision processes
- Non-randomized strategies in stochastic decision processes
- On Stationary Strategies in Countable State Total Reward Markov Decision Processes
- Controlled Markov Processes with Arbitrary Numerical Criteria
- An $\varepsilon $-Optimal Control of a Finite Markov Chain with an Average Reward Criterion
- Ordinal Dynamic Programming
- On the Existence of Good Markov Strategies
- Persistently ϵ-Optimal Strategies
- Optimal decision procedures for finite Markov chains. Part III: General convex systems
- A Note on Memoryless Rules for Controlling Sequential Control Processes
- On Sequential Control Processes
- Negative Dynamic Programming
This page was built for publication: Finite state Markov decision models with average reward criteria
