KIT | KIT-Bibliothek | Impressum
Open Access Logo
DOI: 10.1016/j.ifacol.2017.08.2537

Inverse Reinforcement Learning for Identification in Linear-Quadratic Dynamic Games

Köpf, Florian; Inga, Jairo; Rothfuß, Simon; Flad, Michael; Hohmann, Sören

Abstract (englisch):
The theory of dynamic games has received considerable attention in a wide range of fields. While great effort has been made to develop new algorithms for finding Nash equilibria in dynamic games, the identification of cost functions has received little attention. We present an identification algorithm for linear quadratic dynamic games, a framework which can be applied in the field of shared control between a human and an automatic controller. In this application, the cost function describing human behavior is identified, taking into account the influence of the automation. Furthermore, we consider that human movement underlies certain variability by using a probabilistic Inverse Reinforcement Learning approach. As identification is performed in a single optimization step, the proposed method is suited for real-time applications. A simulation example shows that the algorithm successfully identifies the cost function of the first player which—in combination with the second player—reproduces the observed system output.

Zugehörige Institution(en) am KIT Institut für Regelungs- und Steuerungssysteme (IRS)
Publikationstyp Zeitschriftenaufsatz
Jahr 2017
Sprache Englisch
Identifikator ISSN: 2405-8963, 1474-6670
KITopen ID: 1000075759
Erschienen in IFAC-PapersOnLine
Band 50
Heft 1
Seiten 14902 - 14908
Schlagworte Game Theory; Identification; Inverse Reinforcement Learning; Inverse Optimal Control; Maximum Entropy; Shared Control
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft KITopen Landing Page