The state-action space of an individual agent in a multiagent team fundamentally dictates how the individual interacts with the rest of the team. Thus, how an agent is defined in the context of its domain has a significant effect on team performance when learning to coordinate. In this work we explore the trade-offs associated with these design choices, for example, having fewer agents in the team that individually are able to process and act on a wider scope of information about the world versus a larger team of agents where each agent observes and acts in a more local region of the domain. We focus our study on a traffic management domain and highlight the trends in learning performance when applying different agent definitions. In addition, we analyze the impact of agent failure for different agent definitions and investigate the ability of the team to learn new coordination strategies when individual agents become unresponsive.

The impact of agent definitions and interactions on multiagent learning for coordination in traffic management domains / Chung, J. J.; Miklic, D.; Sabattini, L.; Tumer, K.; Siegwart, R.. - In: AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS. - ISSN 1387-2532. - 34:1(2020), pp. 1-27. [10.1007/s10458-020-09442-1]

The impact of agent definitions and interactions on multiagent learning for coordination in traffic management domains

Miklic D.;Sabattini L.;
2020

Abstract

The state-action space of an individual agent in a multiagent team fundamentally dictates how the individual interacts with the rest of the team. Thus, how an agent is defined in the context of its domain has a significant effect on team performance when learning to coordinate. In this work we explore the trade-offs associated with these design choices, for example, having fewer agents in the team that individually are able to process and act on a wider scope of information about the world versus a larger team of agents where each agent observes and acts in a more local region of the domain. We focus our study on a traffic management domain and highlight the trends in learning performance when applying different agent definitions. In addition, we analyze the impact of agent failure for different agent definitions and investigate the ability of the team to learn new coordination strategies when individual agents become unresponsive.
2020
34
1
1
27
The impact of agent definitions and interactions on multiagent learning for coordination in traffic management domains / Chung, J. J.; Miklic, D.; Sabattini, L.; Tumer, K.; Siegwart, R.. - In: AUTONOMOUS AGENTS AND MULTI-AGENT SYSTEMS. - ISSN 1387-2532. - 34:1(2020), pp. 1-27. [10.1007/s10458-020-09442-1]
Chung, J. J.; Miklic, D.; Sabattini, L.; Tumer, K.; Siegwart, R.
File in questo prodotto:
File Dimensione Formato  
20JAAMAS.pdf

Accesso riservato

Tipologia: Versione pubblicata dall'editore
Dimensione 4.26 MB
Formato Adobe PDF
4.26 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1204146
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 3
social impact