Fostering creativity in the mixed-initiative evolutionary dungeon designer

Abstract

Mixed-initiative systems highlight the collaboration between humans and computers in fostering the generation of more interesting content in game design. In light of the ever-increasing cost of game development, providing mixed-initiative tools can not only significantly reduce the cost but also encourage more creativity amongst game designers. The Evolutionary Dungeon Designer (EDD) [3] is a mixed-initiative tool with a focus on using evolutionary computation to procedurally generate content that adhere to game design patterns. As part of an ongoing project, feedback from a user study on EDD's capabilities as a mixed-initiative design tool pointed out the need for improvement on the tool's functionalities [4]. In this paper we present a review of the principles of the mixedinitiative model, as well as the existing approaches that implement it. The outcome of this analysis allows us to address the appointed needs for improvement by shaping a new version of EDD that we describe here. Finally, we also present the results from a user study carried out with professional game developers, in order to assess EDD's new functionalities. Results show an overall positive evaluation of the tool's intuitiveness and capabilities for empowering game developers' creative skills during the design process of dungeons for adventure games. They also allow us to identify upcoming challenges pattern-based mixed-initiative tools could benefit from. CCS CONCEPTS • Theory of computation → Evolutionary algorithms; • Applied computing → Computer games; • Software and its engineering → Interactive games;

Empowering Quality Diversity in Dungeon Design with Interactive Constrained MAP-Elites

“…EDD's underlying evolutionary algorithm provides procedurally generated suggestions, and is driven through the use of game design microand meso-patterns ( Figure 1.c and Figure 1.d). A detailed description of all EDD's features can be found in [20]- [23].…”

Learning the Designer’s Preferences to Drive Evolution

“…Both options fluently alternate during the creation process by means of a workflow of mutual inspiration, through which all manual editions performed by the user are fed into the underlying continuous Evolutionary Algorithm, accommodating them into the procedural suggestions. A detailed description of EDD and its features can be found in [2,3,4,5].…”

“…Subsequent user studies [3,5] carried out with game designers on EDD raised the following areas of improvement: (1) the designers struggled with EDDs capability of understanding the designers intentions and preserving custom designs;…”

“…In all the above MI-CC approaches, the designers play an active role in the procedurally generated content while struggling between the expressiveness of the automatic generation and the control that they want to exert over it [3]. Having this as motivation, this paper takes the work in [1] one step forward by adding an underlying interactive PCG via machine learning algorithm [29], the Designer Preference Model, that models the user's design style, to be able to predict future designer's choices and thus, driving the content generation with a combination of the designer's subjectivity and the search for quality-diverse content.…”

Pitako - Recommending Game Design Elements in Cicero

“…It also applies heuristics based on game design patterns to assist users in the creation of dungeon maps for adventure games. The tool follows an interaction design approach with every new verision based on previous users' feedback [40], [41]. All of theses examples show that it is possible to use recommender system techniques to assist human tasks.…”