Back to Search
Start Over
GPI-Based design for partially unknown nonlinear two-player zero-sum games.
- Source :
-
Journal of the Franklin Institute . Feb2023, Vol. 360 Issue 3, p2068-2088. 21p. - Publication Year :
- 2023
-
Abstract
- This article focuses on obtaining the solution of two-player zero-sum games (ZSGs) where the saddle point may not exist. From the standpoints of the upper performance index function (PIF) and lower PIF separately, we seek the solution of two-player differential ZSGs without assuming the strict existence of saddle point. To achieve the objective, we apply the generalized policy iteration (GPI) technique to design the controller. With neural network approximators, the system trajectory data are used to update the approximation of the PIFs. It is established that the upper (lower) PIF sequence is convergent along the iteration axis under the GPI scheme. When the two function sequences converge to equal values, the saddle point is attained, and vice versa. Numerical simulation results conformed to the suitability of the designed algorithm. [ABSTRACT FROM AUTHOR]
- Subjects :
- *ZERO sum games
*DESIGN techniques
*COMPUTER simulation
Subjects
Details
- Language :
- English
- ISSN :
- 00160032
- Volume :
- 360
- Issue :
- 3
- Database :
- Academic Search Index
- Journal :
- Journal of the Franklin Institute
- Publication Type :
- Periodical
- Accession number :
- 161766819
- Full Text :
- https://doi.org/10.1016/j.jfranklin.2022.12.028