Abstract
Stationary equilibria in discounted and limiting average finite state/action space stochastic games are shown to be equivalent to global optima of certain nonlinear programs. For zero sum limiting average games, this formulation reduces to a linear objective, nonlinear constraints program, which finds the "best" stationary strategies, even when epsilon-optimal stationary strategies do not exist, for arbitrarily small epsilon.
Original language | English |
---|---|
Pages (from-to) | 227-237 |
Journal | Mathematical Programming |
Volume | 50 |
Issue number | 2 |
DOIs | |
Publication status | Published - Apr 1991 |
Keywords
- STOCHASTIC GAME THEORY