This paper addresses convergence and equilibrium properties of game theoretic learning algorithms in robot populations using simple and broadly applicable reward/cost models of cooperation between robotic agents. New models for robot cooperation are proposed by combining regret based learning methods and network evolution models. Results of mean-field game theory are employed in order to show the asymptotic second moment boundedness in the variation of cooperative behaviour. The behaviour of the proposed models are tested in simulation results, which are based on sample networks and a single lane traffic flow case study.

Smyrnakis, M., Bauso, D., Trodden, P., Veres, S. (2017). Learning of Cooperative Behaviour in Robot Populations. In Proceedings of European Control Conference 2016 [10.1109/ECC.2016.7810284].

Learning of Cooperative Behaviour in Robot Populations

D. Bauso;
2017-01-01

Abstract

This paper addresses convergence and equilibrium properties of game theoretic learning algorithms in robot populations using simple and broadly applicable reward/cost models of cooperation between robotic agents. New models for robot cooperation are proposed by combining regret based learning methods and network evolution models. Results of mean-field game theory are employed in order to show the asymptotic second moment boundedness in the variation of cooperative behaviour. The behaviour of the proposed models are tested in simulation results, which are based on sample networks and a single lane traffic flow case study.
2017
Settore MAT/09 - Ricerca Operativa
Settore ING-INF/04 - Automatica
978-1-5090-2591-6
Smyrnakis, M., Bauso, D., Trodden, P., Veres, S. (2017). Learning of Cooperative Behaviour in Robot Populations. In Proceedings of European Control Conference 2016 [10.1109/ECC.2016.7810284].
File in questo prodotto:
File Dimensione Formato  
ecc2016_cl.pdf

accesso aperto

Tipologia: Pre-print
Dimensione 515.07 kB
Formato Adobe PDF
515.07 kB Adobe PDF Visualizza/Apri
Learning_of_cooperative_behaviour_in_robot_populations.pdf

Solo gestori archvio

Tipologia: Versione Editoriale
Dimensione 412.42 kB
Formato Adobe PDF
412.42 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10447/253219
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 1
social impact