Abstract
Consider the class of n-stage decision models with state space S, action space A, and payoff function g : (S × A)n × S → ℝ. The function g is Markov-achievable if for any possible set of available randomized actions and all transition laws, each plan has a corresponding Markov plan whose value is at least as good. A condition on g, called the "non-forking linear sections property", is necessary and sufficient for g to be Markov achievable. If g satisfies the slightly stronger "general linear sections property", then g can be written as a sum of products of certain simple neighboring-stage payoffs.
| Original language | English (US) |
|---|---|
| Pages (from-to) | 101-118 |
| Number of pages | 18 |
| Journal | Stochastic Processes and their Applications |
| Volume | 73 |
| Issue number | 1 |
| DOIs | |
| State | Published - Jan 15 1998 |
Keywords
- Markov decision model
- Markov plan
- Payoff function
ASJC Scopus subject areas
- Statistics and Probability
- Modeling and Simulation
- Applied Mathematics
Fingerprint Dive into the research topics of 'Markov-achievable payoffs for finite-horizon decision models'. Together they form a unique fingerprint.
Cite this
Pestien, V., & Wang, X. (1998). Markov-achievable payoffs for finite-horizon decision models. Stochastic Processes and their Applications, 73(1), 101-118. https://doi.org/10.1016/S0304-4149(97)00095-1