Selfish vs. global behavior promotion in car controller evolution
| Autor: | Eric Medvet, Jacopo Talamini, Alberto Bartoli, Giovanni Scaini |
|---|---|
| Přispěvatelé: | Talamini, Jacopo, Scaini, Giovanni, Medvet, Eric, Bartoli, Alberto |
| Jazyk: | angličtina |
| Rok vydání: | 2018 |
| Předmět: |
Mathematical optimization
Neuroevolution Computer science Modern evolutionary synthesis media_common.quotation_subject NEAT Collective behavior 02 engineering and technology ComputingMethodologies_ARTIFICIALINTELLIGENCE Task (project management) Promotion (rank) Control theory 020204 information systems 0202 electrical engineering electronic engineering information engineering Driverless car 020201 artificial intelligence & image processing media_common |
| Zdroj: | GECCO (Companion) |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|