Article ID: | iaor19961315 |
Country: | United States |
Volume: | 34 |
Issue: | 1 |
Start Page Number: | 311 |
End Page Number: | 328 |
Publication Date: | Jan 1996 |
Journal: | SIAM Journal on Control and Optimization |
Authors: | Altman Eitan, Tidball Mabel |
The authors develop a unifying approach for approximating a ‘limit’ zero-sum game by a sequence of approximating games. They discuss both the convergence of the values and the convergence of optimal (or ‘almost’ optimal) strategies. Moreover, based on optimal policies for the limit game, the authors construct policies which are almost optimal for the approximating games. They then apply the general framework to state approximations of stochastic games, to convergence of finite horizon problems to infinite horizon problems, and to convergence in the discount factor and in the immediate reward.