Abstract
The demand for automated game development assistance tools can be fulfilled by computational creativity algorithms. The procedural generation is one of the topics for creative content development. The main procedural generation challenge for game level layout is how to create a diverse set of levels that could match a human-crafted game scene. Our game scene layouts are created randomly and then sculpted using a genetic algorithm. To address the issue of fitness calculation with conflicting criteria, we use weighted aggregated sum product assessment (WASPAS) in a single-valued neutrosophic set environment (SVNS) that models the indeterminacy with truth, intermediacy, and falsehood memberships. Results are presented as an encoded game object grid where each game object type has a specific function. The algorithm creates a diverse set of game scene layouts by combining game rules validation and aesthetic principles. It successfully creates functional aesthetic patterns without specifically defining the shapes of the combination of games’ objects.
Highlights
Procedural Video Game SceneToday, researchers are discovering more and more new results in the artificial intelligence domain [1]
There is a new emerging usage of neutrosophic sets combined with multicriteria decision making (MCDM), but this approach is not widely explored in the field of machine learning, but it can benefit the creativity of such models [19,20,21,22]
Final fitness is calculated using an agent that plays the game. This method reduces the computational cost for this problem and adds new solutions to calculate the rewards of the genetic algorithm, not focusing too much on the penalty
Summary
Researchers are discovering more and more new results in the artificial intelligence domain [1]. The product target is widely used in machine learning tasks, as most training data sets are made up of the available creative work—these systems usually create an independent logic loop of creativity directly unrelated to the original work process [3]. We are focusing on the process-related target, as it usually generates more example-independent results, which is one of computational creativity tasks This means that the generated work differs more from the training data set. There is a new emerging usage of neutrosophic sets combined with multicriteria decision making (MCDM), but this approach is not widely explored in the field of machine learning, but it can benefit the creativity of such models [19,20,21,22]. We add a more detailed explanation of related work, methodology, created framework, results, and conclusions
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
