Single sample path-based optimization of Markov chains
From MaRDI portal
Publication:1289394
DOI10.1023/A:1022634422482zbMath0949.90092OpenAlexW1497026160MaRDI QIDQ1289394
Publication date: 28 November 2000
Published in: Journal of Optimization Theory and Applications (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1023/a:1022634422482
Related Items (7)
A time aggregation approach to Markov decision processes ⋮ Potential-based least-squares policy iteration for a parameterized feedback control system ⋮ The control of a two-level Markov decision process by time aggregation ⋮ Generalized estimates for performance sensitivities of stochastic systems ⋮ Temporal difference-based policy iteration for optimal control of stochastic systems ⋮ A unified approach to Markov decision problems and performance sensitivity analysis with discounted and average criteria: multichain cases ⋮ Basic ideas for event-based optimization of Markov systems
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Markov chains and stochastic stability
- Sample-path optimization of convex stochastic performance functions
- Feature-based methods for large scale dynamic programming
- Using the QR Factorization and Group Inversion to Compute, Differentiate, and Estimate the Sensitivity of Stationary Probabilities for Markov Chains
- Stochastic optimization of regenerative systems using infinitesimal perturbation analysis
- Perturbation realization, potentials, and sensitivity analysis of Markov processes
- The policy iteration algorithm for average reward Markov decision processes with general state space
- Discrete-Time Controlled Markov Processes with Average Cost Criterion: A Survey
- Likelihood ratio gradient estimation for stochastic recursions
- Perturbation theory and finite Markov chains
This page was built for publication: Single sample path-based optimization of Markov chains