Intelligent social learning

One of the cognitive processes responsible for social propagation iis socia l learning, broadly meant as the process by means of which agents' acquisit ion of new information is caused or favoured by their being exposed to one another in a common environment. Social learning results from one or other of a number of social phenomena, the most important of which are social fac ilitation and imitation. In this paper, a general notion of social learning will be defined and the main processes that are responsible for it, namely social facilitation and imitation, will be analysed in terms of the social mental processes they require. A brief analysis of classical definitions o f social learning is carried on, showing that a systematic and consistent t reatment of this notion is still missing. A general notion of social learni ng is then introduced and the two main processes that may lead to it, socia l facilitation and imitation, will be defined as different steps on a conti nuum of cognitive complexity. Finally, the utility of the present approach is discussed. The analysis presented in this paper draws upon a cognitive m odel of social action (cf. Conte & Castelfranchi 1995; Conte 1999). The age nt model that will be referred to throughout the paper is a cognitive model , endowed with mental properties for pursuing goals and intentions, and for knowledge-based action. To be noted, a cognitive agent is not to be necess arily meant as a natural system, although many examples examined in the pap er are drawn from the real social life of humans. Cognitive agents may also be artificial systems endowed with the capacity for reasoning, planning, a nd decision-making about both world and mental states. Finally, some advant ages of intelligent social learning in agent systems applications are discu ssed.