Search

Your search keyword '"ZERO sum games"' showing total 2 results
2 results on '"ZERO sum games"'

1. Event-triggered adaptive dynamic programming for discrete-time multi-player games.

Author

Wang, Ziyang, Wei, Qinglai, and Liu, Derong

Subjects
*DYNAMIC programming, *DISCRETE-time systems, *NEURAL circuitry, *POLYNOMIALS, *ZERO sum games
Abstract

For multi-player games, the event-triggered adaptive dynamic programming (ADP) method with single triggering condition cannot be used. In this paper, an event-triggered ADP method with multiple triggering conditions is developed for multi-player non-zero-sum (NZS) games. Triggering conditions are designed for each player, and the control inputs will be updated only when the relevant conditions are satisfied. Besides, the developed method is implemented by single-network structure. Therefore, the computational burden can be reduced effectively. Additionally, the stability is analyzed for event-triggered multi-player systems. Finally, two examples are employed to show the effectiveness of the developed method. [ABSTRACT FROM AUTHOR]

Published
2020
Full Text
View/download PDF

2. Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm

Author

Liu, Derong, Li, Hongliang, and Wang, Ding

Subjects
*ZERO sum games, *ARTIFICIAL neural networks, *DISCRETE-time systems, *NONLINEAR systems, *ITERATIVE methods (Mathematics), *DYNAMIC programming, *COMPUTER algorithms
Abstract

Abstract: In this paper, we solve the zero-sum game problems for discrete-time affine nonlinear systems with known dynamics via iterative adaptive dynamic programming algorithm. First, a greedy heuristic dynamic programming iteration algorithm is developed to solve the zero-sum game problems, which can be used to solve the Hamilton–Jacobi–Isaacs equation associated with optimal regulation control problems. The convergence analysis in terms of value function and control policy is provided. To facilitate the implementation of the algorithm, three neural networks are used to approximate the control policy, the disturbance policy, and the value function, respectively. Then, we extend the algorithm to optimal tracking control problems through system transformation. Finally, two simulation examples are presented to demonstrate the effectiveness of the proposed scheme. [Copyright &y& Elsevier]

Published
2013
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results