On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case (Q3763919)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case |
scientific article |
Statements
On the Convergence of Policy Iteration in Finite State Undiscounted Markov Decision Processes: The Unichain Case (English)
0 references
1987
0 references
convergence of policy iteration
0 references
undiscounted, finite state, discrete time Markov decision
0 references
compact action space
0 references
unichain transition structure
0 references
Newton method type
0 references
average optimal policy
0 references