The proposed structure of learning facilities is self-developed via a trial and errors process: the reinforcement learning model is built upon the Swarm-Like Agent Protocol in Python (SLAPP), a recent implementation of the standard Swarm function library for agent-based simulation, written using Python, a powerful and quite simple language. We introduce also a very complicated crossroad, with: (i) learning in agents as first element, to be able to understand how agents modify their behavior, (ii) BDI (Beliefs, Desires, Intentions) definition to clarify the motivation of that behavior. To the cross-road we have to connect two open directions: (a) that of the micro-macro link, which is a key step in understanding the world we are immersed in; (b) the interaction between our agents, in networks. Finally, we go to the question if agent-based simulation could help in a perspective of policy management and law creation or norm emergence. Several examples help to deepen the discussion.

Learning agents and decisions: new perspectives

TERNA, Pietro
2013-01-01

Abstract

The proposed structure of learning facilities is self-developed via a trial and errors process: the reinforcement learning model is built upon the Swarm-Like Agent Protocol in Python (SLAPP), a recent implementation of the standard Swarm function library for agent-based simulation, written using Python, a powerful and quite simple language. We introduce also a very complicated crossroad, with: (i) learning in agents as first element, to be able to understand how agents modify their behavior, (ii) BDI (Beliefs, Desires, Intentions) definition to clarify the motivation of that behavior. To the cross-road we have to connect two open directions: (a) that of the micro-macro link, which is a key step in understanding the world we are immersed in; (b) the interaction between our agents, in networks. Finally, we go to the question if agent-based simulation could help in a perspective of policy management and law creation or norm emergence. Several examples help to deepen the discussion.
2013
1
115
129
http://www.ittig.cnr.it/EditoriaServizi/AttivitaEditoriale/InformaticaEDiritto/Risultati.php
Pietro Terna
File in questo prodotto:
Non ci sono file associati a questo prodotto.

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/2318/147005
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact