Turn-based evolution in a simplified model of artistic creative process

Studies of mind, thought, and reason have tended to marginalize the role of bodily form, real-world action, and environmental backdrop. In recent years, both in philosophy and cognitive science, this tendency has been identified and, increasingly, resisted. The result is a plethora of work on what has become known as embodied, situated, distributed, and even ‘extended’ cognition. Work in this new, loosely-knit field depicts thought and reason as in some way inextricably tied to the details of our gross bodily form, our habits of action and intervention, and the enabling web of social, cultural, and technological scaffolding in which we live, move, learn, and think. But exactly what kind of link is at issue? And what difference might such a link or links make to our best philosophical, psychological, and computational models of thought and reason? These are among the large unsolved problems in this increasingly popular field. This book offers both a tour of the emerging landscape, and an argument in favour of one approach to the key issues. That approach combines the use of representational, computational, and information-theoretic tools with an appreciation of the importance of context, timing, biomechanics, and dynamics. More controversially, it depicts some coalitions of biological and non-biological resources as the extended cognitive circuitry of individual minds.

In evolutionary computation, the fitness function normally measures progress toward an objective in the search space, effectively acting as an objective function. Through deception, such objective functions may actually prevent the objective from being reached. While methods exist to mitigate deception, they leave the underlying pathology untreated: Objective functions themselves may actively misdirect search toward dead ends. This paper proposes an approach to circumventing deception that also yields a new perspective on open-ended evolution. Instead of either explicitly seeking an objective or modeling natural evolution to capture open-endedness, the idea is to simply search for behavioral novelty. Even in an objective-based problem, such novelty search ignores the objective. Because many points in the search space collapse to a single behavior, the search for novelty is often feasible. Furthermore, because there are only so many simple behaviors, the search for novelty leads to increasing complexity. By decoupling open-ended search from artificial life worlds, the search for novelty is applicable to real world problems. Counterintuitively, in the maze navigation and biped walking tasks in this paper, novelty search significantly outperforms objective-based search, suggesting the strange conclusion that some problems are best solved by methods that ignore the objective. The main lesson is the inherent limitation of the objective-based paradigm and the unexploited opportunity to guide search through other means.