Model-based reinforcement learning in differential graphical games

DOI10.1109/TCNS.2016.2617622MaRDI QIDQ6283706arXivFDO

Authors Rushikesh Kamalapurkar, Justin R. Klotz, Patrick Walters, Warren E. Dixon

Publication date 27 February 2017

Published in arXiv

Full work available at URL https://doi.org/10.1109/TCNS.2016.2617622

Mathematics Subject Classification ID

Differential games and control (49N70) Differential games (aspects of game theory) (91A23) Multi-agent systems (93A16) Feedback control (93B52)

arXiv classification

cs.SYmath.OC

Abstract: This paper seeks to combine differential game theory with the actor-critic-identifier architecture to determine forward-in-time, approximate optimal controllers for formation tracking in multi-agent systems, where the agents have uncertain heterogeneous nonlinear dynamics. A continuous control strategy is proposed, using communication feedback from extended neighbors on a communication topology that has a spanning tree. A model-based reinforcement learning technique is developed to cooperatively control a group of agents to track a trajectory in a desired formation. Simulation results are presented to demonstrate the performance of the developed technique.

This page was built for publication: Model-based reinforcement learning in differential graphical games

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6283706)