https://www.um.edu.mt/library/oar/handle/123456789/19740 2026-07-14T04:41:35Z 2026-07-14T04:41:35Z https://www.um.edu.mt/library/oar/handle/123456789/147981 2026-07-10T08:31:12Z 2026-01-01T00:00:00Z

Title: A world beyond our understanding : madman’s knowledge Abstract: The item 'Madman’s Knowledge' in FromSoftware's 2016 action-adventure Bloodborne is a game element that contributes to the developer's infamous pursuit of a ludic aesthetics of failure. This particular object leverages two kinds of obfuscation of game-related information: one that places it forever beyond the player’s grasp, and one that can eventually be dispelled through direct experience and recourse to secondary sources. While the latter can be turned into familiar drivel, the former (often referred to as fictional incompleteness) is a mystery that is meant to remain unsolved. In their unique ways, both kinds of informational deficiency evoke fictional worlds whose mystery and greatness extend beyond the limited scope and content of any creative work.

2026-01-01T00:00:00Z Yuan, Yi Zhang, Qingquan Yuan, Bo Barthet, Matthew Khalifa, Ahmed Yannakakis, Georgios N. Chen, Huanhuan Liu, Jialin https://www.um.edu.mt/library/oar/handle/123456789/147356 2026-06-11T12:37:44Z 2026-01-01T00:00:00Z

Title: MOPCGRL : Multi-objective procedural content generation via reinforcement learning Authors: Yuan, Yi; Zhang, Qingquan; Yuan, Bo; Barthet, Matthew; Khalifa, Ahmed; Yannakakis, Georgios N.; Chen, Huanhuan; Liu, Jialin Abstract: Online content generation enables automatic and adaptive creation of diverse and playable game content for maximizing player experience or testing Artificial Intelligence (AI) algorithms. Multiple diversity metrics have been formulated on different content facets in the literature, while some of them conflict with one another. Existing work addresses this multi-dimensional diversity nature by converting those metrics into one term that is further used to direct the training of content generators. However, each generator is trained to meet the preference specified by the weights and fails to fully interpret the relationships among these metrics or provide different trade-offs. This paper proposes a multi-objective procedural content generation via reinforcement learning to train a set of generators that create diverse game content in an online manner while balancing the trade-off between multiple diversity metrics with playability as a constraint. Our framework is compared with state-of-the-art approaches on the commonly used Mario-AI benchmark. Results show that our framework is capable of increasing the diversity of the generator distribution while accelerating the convergence during the early stages of model training. Our approach enables researchers, designers, and practitioners to gain a better understanding of the relationship among conflicting diversity metrics, allowing them to generate content more efficiently and accurately tailored to specific needs.

2026-01-01T00:00:00Z Bhaumik, Debosmita Togelius, Julian Yannakakis, Georgios N. Khalifa, Ahmed https://www.um.edu.mt/library/oar/handle/123456789/147355 2026-06-11T12:10:52Z 2025-07-01T00:00:00Z

Title: Evolutionary level repair Authors: Bhaumik, Debosmita; Togelius, Julian; Yannakakis, Georgios N.; Khalifa, Ahmed Abstract: We address the problem of game level repair, which consists of taking a designed but non-functional game level and making it functional. This might consist of ensuring the completeness of the level, reachability of objects, or other performance characteristics. The repair problem may also be constrained in that it can only make a small number of changes to the level. We investigate search-based solutions to the level repair problem, particularly using evolutionary and quality-diversity algorithms, with good results. This level repair method is applied to levels generated using a machine learning-based procedural content generation (PCGML) method that generates stylistically appropriate but frequently broken levels. This combination of PCGML for generation and search-based methods for repair shows great promise as a hybrid procedural content generation (PCG) method.

2025-07-01T00:00:00Z Müller-Brockhausen, Matthias Khalifa, Ahmed Preuss, Mike https://www.um.edu.mt/library/oar/handle/123456789/147351 2026-06-11T11:54:15Z 2025-01-01T00:00:00Z

Title: Scalable procedural content generation via transfer reinforcement learning Authors: Müller-Brockhausen, Matthias; Khalifa, Ahmed; Preuss, Mike Abstract: Procedural Content Generation algorithms that make use of Machine Learning have garnered significant attention from the general public due to their ability to generate text, images, or video content that is often indistinguishable from human-crafted artworks. These achievements typically necessitate a substantial quantity of data, which may be scarce in specialized domains such as game-level design. One machine learning technique, Reinforcement Learning (RL), can be employed to learn from trial and error to address this scarcity. However, the RL training process requires a substantial time investment and may prove unsuccessful in the case of sparse reward structures. This paper empirically demonstrates the efficacy of curriculum learning as a viable solution to address scalability issues inherent to learning more complex tasks. Instead of trying to learn the whole space from scratch, we employ transfer learning on a curriculum from small to larger levels. We empirically validated this in a 3D vector-based environment, where the objective is to generate free-form tracks that facilitate a rider to move between designated points in the same vain as the flash game hit “Linerider”.

2025-01-01T00:00:00Z