Average Reward Markov Decision Processes with Multiple Cost Constraints
From MaRDI portal
Publication:4718597
DOI10.1080/02522667.1995.10699238zbMath0862.90128OpenAlexW2318172716MaRDI QIDQ4718597
Publication date: 25 May 1997
Published in: Journal of Information and Optimization Sciences (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/02522667.1995.10699238
occupation measuresstationary policyconstrained Markov decision processescompact state and action spaceslong-run average rewardstate-wise mixed stationary policy
Cites Work
- Unnamed Item
- Optimal policies for controlled Markov chains with a constraint
- Stochastic optimal control. The discrete time case
- Finite state Markovian decision processes
- Multichain Markov Decision Processes with a Sample Path Constraint: A Decomposition Approach
- Time-average optimal constrained semi-Markov decision processes
- Randomized and Past-Dependent Policies for Markov Decision Processes with Multiple Constraints
- The Existence of a Minimum Pair of State and Policy for Markov Decision Processes under the Hypothesis of Doeblin
- Ergodic Control of Markov Chains with Constraints—the General Case
- Denumerable Constrained Markov Decision Processes and Finite Approximations
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Markov Decision Processes with Sample Path Constraints: The Communicating Case