We consider collective tasks to be solved by simple agents synthesized automatically by means of neuroevolution. We investigate whether driving neuroevolution by promoting a form of selfish behavior, i.e., by optimizing a fitness index that synthesizes the behavior of each agent independent of any other agent, may also result in optimizing global, system-wide properties. We focus on a specific and challenging task, i.e., evolutionary synthesis of agent as car controller for a road traffic scenario. Based on an extensive simulation-based analysis, our results indicate that even by optimizing the behavior of each single agent, the resulting system-wide performance is comparable to the performance resulting from optimizing the behavior of the system as a whole. Furthermore, agents evolved with a fitness promoting selfish behavior appear to lead to a system that is globally more robust with respect to the presence of unskilled agents.

Selfish vs. global behavior promotion in car controller evolution

Talamini, Jacopo;Scaini, Giovanni;Medvet, Eric;Bartoli, Alberto
2018-01-01

Abstract

We consider collective tasks to be solved by simple agents synthesized automatically by means of neuroevolution. We investigate whether driving neuroevolution by promoting a form of selfish behavior, i.e., by optimizing a fitness index that synthesizes the behavior of each agent independent of any other agent, may also result in optimizing global, system-wide properties. We focus on a specific and challenging task, i.e., evolutionary synthesis of agent as car controller for a road traffic scenario. Based on an extensive simulation-based analysis, our results indicate that even by optimizing the behavior of each single agent, the resulting system-wide performance is comparable to the performance resulting from optimizing the behavior of the system as a whole. Furthermore, agents evolved with a fitness promoting selfish behavior appear to lead to a system that is globally more robust with respect to the presence of unskilled agents.
2018
9781450357647
https://dl.acm.org/citation.cfm?id=3208254
File in questo prodotto:
File Dimensione Formato  
gecco-selfish-p1722-talamini.pdf

Accesso chiuso

Descrizione: Articolo principale
Tipologia: Documento in Versione Editoriale
Licenza: Copyright Editore
Dimensione 675.96 kB
Formato Adobe PDF
675.96 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

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/11368/2927472
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact