Computing Optimal Policies for Markovian Decision Processes Using Simulation
From MaRDI portal
Publication:2808287
DOI10.1017/S0269964800004034zbMath1336.90100MaRDI QIDQ2808287
Michael N. Katehakis, Apostolos N. Burnetas
Publication date: 23 May 2016
Published in: Probability in the Engineering and Informational Sciences (Search for Journal in Brave)
Related Items (2)
On confidence intervals from simulation of finite Markov chains ⋮ Stochastic finite-state systems in control theory
Cites Work
- Unnamed Item
- Nonstationary Markov decision problems with converging parameters
- Adaptive Markov control processes
- Computational comparison of value iteration algorithms for discounted Markov decision processes
- Finite state Markovian decision processes
- Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
- A Survey of Some Results in Stochastic Adaptive Control
- Using Simulation to Estimate First Passage Distribution
- Perturbation theory for Markov reward processes with applications to queueing systems
- Simulating Stable Stochastic Systems, I: General Multiserver Queues
- Simulating Stable Stochastic Systems, II: Markov Chains
This page was built for publication: Computing Optimal Policies for Markovian Decision Processes Using Simulation
