Back to Search
Start Over
Mix-zero-sum differential games for linear systems with unknown dynamics based on off-policy IRL.
- Source :
-
Neurocomputing . Jul2020, Vol. 398, p280-290. 11p. - Publication Year :
- 2020
-
Abstract
- This paper discusses a multi-player mixed-zero-sum (MZS) differential games with completely unknown dynamics. Based on off-policy integral reinforcement learning (IRL), a novel algorithm is proposed to obtain the optimal control. First, a policy iteration algorithm is put forward to obtain the optimal solution for deterministic system. Next, the case that the system dynamics is completely unknown is considered. And an IRL-based off-policy algorithm is presented. Meanwhile, the convergence of the presented algorithms is proved in this paper. At the end, the effectiveness of the proposed algorithm is shown by a simulation. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09252312
- Volume :
- 398
- Database :
- Academic Search Index
- Journal :
- Neurocomputing
- Publication Type :
- Academic Journal
- Accession number :
- 143364499
- Full Text :
- https://doi.org/10.1016/j.neucom.2020.02.078