Abstract
If X is a countable state space and g is a bounded reward function on Xn, then say g has the Markov-adequacy property if every strategy has a corresponding randomized Markov strategy which gives g the same integral as the original strategy. A complete characterization of functions having the Markov-adequacy property is given. In particular, if g is permutation-invariant and X has at least three elements, then g has the Markov-adequacy property if and only if g has the linear sections property, a condition which is easy to verify.
Original language | English (US) |
---|---|
Pages (from-to) | 129-151 |
Number of pages | 23 |
Journal | Stochastic Processes and their Applications |
Volume | 46 |
Issue number | 1 |
DOIs | |
State | Published - May 1993 |
Keywords
- Markov strategy
- randomized strategy
- rewars function
ASJC Scopus subject areas
- Statistics and Probability
- Modeling and Simulation
- Applied Mathematics