Capturing Local and Global Patterns in Procedural Content Generation via Machine Learning

Abstract

Recent procedural content generation via machine learning (PCGML) methods allow learning from existing content to produce similar content automatically. While these approaches are able to generate content for different games (e.g. Super Mario Bros., DOOM, Zelda, and Kid Icarus), it is an open questions how well these approaches can capture large-scale visual patterns such as symmetry. In this paper, we propose match-three games as a domain to test PCGML algorithms regarding their ability to generate suitable patterns. We demonstrate that popular algorithm such as Generative Adversarial Networks struggle in this domain and propose adaptations to improve their performance. In particular we augment the neighborhood of a Markov Random Fields approach to not only take local but also symmetric positional information into account. We conduct several empirical tests including a user study that show the improvements achieved by the proposed modifications, and obtain promising results.

Privacy and Security Concerns in Generative AI: A Comprehensive Survey

“…Generative AI has made a significant contribution to different sectors ranging from Healthcare [69], [70], [71] to Education [72], [73], from Finance to Arts [74], [75], from Autonomous Vehicles [76], [77] to Drug Discovery [78], [79], and more. In the above sections, we discussed the overall positive impacts of this advanced technology.…”

Procedural Video Game Scene Generation by Genetic and Neutrosophic WASPAS Algorithms

“…It tries to apply the procedural video game generation problem to a variety of games with differing rules. Another example is focused on creative patterns [29]. The match 3 type game is used as a base for the generator.…”

“…Usefulness is defined by the safe zone and player exit dis tance criteria. Criteria were selected based on recurrence in the literature [26][27][28][29][30], game design principles, and creativity definitions [2,4,5]. If one of the constraint functions does not pass, the total fitness is multiplied by zero.…”

World-GAN: a Generative Model for Minecraft Worlds

“…The field of PCGML has seen many advances in recent years, due to the growing capabilities of Machine Learning algorithms. Besides classical methods like Markov Random Fields and GANs [11], its methods have been used for level generation in Candy Crush Saga and Super Mario Bros. (SMB) [5]. A recent approach framed PCG as a Reinforcement Learning (RL) problem and generated Zelda and Sokoban levels [12] using a Deep RL agent.…”