Concurrent learning-based online approximate feedback-Nash equilibrium solution of N-player nonzero-sum differential games

Autor:	Kamalapurkar, Rushikesh, Klotz, Justin, Dixon, Warren E.
Rok vydání:	2013
Předmět:	Computer Science - Systems and Control Mathematics - Optimization and Control
Druh dokumentu:	Working Paper
DOI:	10.1109/JAS.2014.7004681
Popis:	This paper presents a concurrent learning-based actor-critic-identifier architecture to obtain an approximate feedback-Nash equilibrium solution to an infinite horizon N-player nonzero-sum differential game online, without requiring persistence of excitation (PE), for a nonlinear control-affine system. Under a condition milder than PE, uniformly ultimately bounded convergence of the developed control policies to the feedback-Nash equilibrium policies is established.
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1310.1384 Zobrazit plný text záznamu View this record from Arxiv