Pages that link to "Item:Q3986172"
From MaRDI portal
The following pages link to Performance gradient estimation for the very large finite Markov chains (Q3986172):
Displaying 10 items.
- A unified approach to time-aggregated Markov decision processes (Q259403) (← links)
- Solving average cost Markov decision processes by means of a two-phase time aggregation algorithm (Q300040) (← links)
- Gradient estimates for the performance of Markov chains and discrete event processes (Q1207844) (← links)
- On performance potentials and conditional Monte Carlo for gradient estimation for Markov chains (Q1290201) (← links)
- A time aggregation approach to Markov decision processes (Q1614322) (← links)
- Optimization via simulation: A review (Q1805482) (← links)
- A basic formula for performance gradient estimation of semi-Markov decision processes (Q2253434) (← links)
- The control of a two-level Markov decision process by time aggregation (Q2641752) (← links)
- Likelihood Ratio Gradient Estimation for Steady-State Parameters (Q5113892) (← links)
- On-line policy gradient estimation with multi-step sampling (Q5962027) (← links)