Journal
NEUROCOMPUTING
Volume 307, Issue -, Pages 54-60Publisher
ELSEVIER
DOI: 10.1016/j.neucom.2018.04.005
Keywords
Adaptive dynamic programming; Approximate dynamic programming; Zero-sum games; Neural networks
Categories
Funding
- IAPI Fundamental Research Funds [2013ZCX14]
- National Natural Science Foundation of China [61433004, 61627809, 61621004]
Ask authors/readers for more resources
This paper presents novel iterative learning methods along with the neural network implementation for multi-player zero-sum games. Solving zero-sum games depends on the solutions of Hamilton-Jacobi-Isaacs equations, which are nonlinear partial differential equations. These solutions are generally difficult or even impossible to be obtained analytically. To overcome this difficulty, iterative adaptive dynamic programming algorithms are utilized. In the related research works, three-network architecture, i.e., critic-actor-disturbance structure, is used to approximate the value function, control policies and disturbance policies. Different from the previous works, this paper employs single-network architecture, i.e., critic-only structure, to implement the proposed algorithms, which reduces the computation burden and the complexity of design procedure. Finally, two simulation examples are provided to illustrate the effectiveness of our proposed methods. (C) 2018 Published by Elsevier B.V.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available