Social Learning in a Multi-Agent System

Noble, Jason and Franks, Daniel W (2004) Social Learning in a Multi-Agent System. Computing and Informatics, 22. pp. 101-114.

Full text not available from this repository.


Abstract. In a persistent multi-agent system, it should be possible for new agents
to bene¯t from the accumulated learning of more experienced agents. Parallel
reasoning can be applied to the case of newborn animals, and thus the biological
literature on social learning may aid in the construction of e®ective multi-agent
systems. Biologists have looked at both the functions of social learning and the
mechanisms that enable it. Many researchers have focused on the cognitively com-
plex mechanism of imitation; we will also consider a range of simpler mechanisms
that could more easily be implemented in robotic or software agents. Research in
arti¯cial life shows that complex global phenomena can arise from simple local rules.
Similarly, complex information sharing at the system level may result from quite
simple individual learning rules. We demonstrate in simulation that simple mecha-
nisms can outperform imitation in a multi-agent system, and that the e®ectiveness
of any social learning strategy will depend on the agents' environment. Our simple
mechanisms have obvious advantages in terms of robustness and design costs

Item Type: Article
Schools and Departments: University of Sussex Business School > SPRU - Science Policy Research Unit
Depositing User: EPrints Services
Date Deposited: 06 Feb 2012 18:39
Last Modified: 02 Apr 2012 08:25
📧 Request an update