A General Framework for Describing Creative Agents
This work addresses the need for a unified theoretical understanding of creative agents in computational creativity, which is incremental as it builds on existing notions but formalizes them for broader application.
The paper tackles the lack of a formal theoretical framework for describing creative agents in AI by introducing General Creativity, which extends traditional notions and allows for unambiguous description of any creative agent and their behavior in societies, including analysis of different forms of creativity and dynamics in mixed human-AI systems.
Computational creativity is a subfield of AI focused on developing and studying creative systems. Few academic studies analysing the behaviour of creative agents from a theoretical viewpoint have been proposed. The proposed frameworks are vague and hard to exploit; moreover, such works are focused on a notion of creativity tailored for humans. In this paper we introduce General Creativity, which extends that traditional notion. General Creativity provides the basis for a formalised theoretical framework, that allows one to univocally describe any creative agent, and their behaviour within societies of creative systems. Given the growing number of AI creative systems developed over recent years, it is of fundamental importance to understand how they could influence each other as well as how to gauge their impact on human society. In particular, in this paper we exploit the proposed framework for (i) identifying different forms of creativity; (ii) describing some typical creative agents behaviour, and (iii) analysing the dynamics of societies in which both human and non-human creative systems coexist.