Generalized maximum entropy estimation of dynamic programming models with sample selection bias (Q1424658)
From MaRDI portal
scientific article
Language | Label | Description | Also known as |
---|---|---|---|
English | Generalized maximum entropy estimation of dynamic programming models with sample selection bias |
scientific article |
Statements
Generalized maximum entropy estimation of dynamic programming models with sample selection bias (English)
0 references
16 March 2004
0 references
The author considers a class of censored Markov decision processes with decision variable censored at zero. The Lagrange multipliers technique is used to incorporate the restrictions. Maximum entropy principle is used in the selection of transition probabilities.
0 references
Markov decision process
0 references
Lagrange multipliers
0 references
transition probability
0 references