Generating Object Placements for Optimum Exploration and Unpredictability in Medium-Coupling Educational Games

Understanding which and how attributes impact player experience can contribute to designing more tailored tools, providing concerns on how to improve these. However, there is a gap in the understanding of what impacts learners’ experience when interacting with Educational Games (EG) featuring Procedural Content generation (PCG) as these have been scantly used together. This article presents an empirical study on which attributes impact both math’s and game’s curiosity of players when interacting with an EG that uses PCG. The results show the attributes that led to higher or lower curiosity, as well aswhich of them are associated with it. Hence, advancing the understanding of what drives players’ curiosity, contributing to the design of EG that feature PCG.

Procedural content generation is helping game developers to create significant quantity of high quality dynamic content for video games at a fraction of cost of the traditional methods. Procedural texture synthesis is a sub category of procedural content generation which helps video games to have significant variations in textures of the environments and the objects across the progress of the game and to avoid repetition. Generative Adversarial Networks are a class of deep learning algorithms which are capable of learning the patterns and creating new patterns. In this paper, Generative Adversarial Networks is used for procedural content generation for original textures synthesis for video game development. This method is used by video game designers for autonomous redesigning of objects and environment textures. This process saves significant time and cost in video game development. The particular attention in this paper is on procedural synthesis of ground surface textures. The generated texture samples are visually acceptable and have mean score of 2.45 with 0.1 standard deviation after 2K iteration. Also the discriminator loss of generated samples reached 0.74 at the final stage of training. The proposed framework can be used as an effective procedural texture synthesis framework for video game design and development.

Procedural content generation (PCG) systems are designed to automatically generate content for video games. PCG for physics-based puzzles requires one to simulate the game to ensure feasibility and stability of the objects composing the puzzle. The major drawback of this simulation-based approach is the overall running time of the PCG process, as the simulations can be computationally expensive. This paper introduces a method that uses machine learning to reduce the number of simulations performed by an evolutionary approach while generating levels of Angry Birds, a physics-based puzzle game. Our method uses classifiers to verify the stability and feasibility of the levels considered during search. The fitness function is computed only for levels that are classified as stable and feasible. An approximation of the fitness that does not require simulations is used for levels that are deemed as unstable or unfeasible by the classifiers. Our experiments show that naively approximating the fitness values can lead to poor solutions. We then introduce an approach in which the fitness values are approximated with the average fitness value of the levels' parents added to a penalty value. This approximation scheme allows the search procedure to find good-quality solutions much more quickly than a competing approach—we reduce from 43 to 25 minutes the running time required to generate one level of Angry Birds.

Procedural Content Generation (PCG) has emerged as a powerful approach for automating game content creation, offering significant benefits in terms of cost reduction and time efficiency compared to traditional game design and development processes (Zhang, Zhang, & Huang, 2022). While Genetic Algorithms (GAs) have been widely used in PCG, alternative metaheuristic algorithms such as Particle Swarm Optimization (PSO) and Artificial Bee Colony (ABC) have demonstrated their effectiveness in delivering high-quality solutions and efficient optimization capabilities across different problem domains (Amato, 2017). However, their application in PCG remains limited. I aim to evaluate the performance of PSO and ABC in map layout generation, challenging the conventional use of GAs. By comparing three metaheuristic algorithms (GA, ABC, and PSO) I seek to assess the effectiveness of these approaches in generating game levels and identify any obvious differences in their performance characteristics. Comprehensive experiments are conducted, applying GA, ABC, and PSO to a map layout generation. Metrics like convergence speed and content quality are used to evaluate the generated game content. My findings reveal that both ABC and PSO demonstrate advantages over traditional GA implementations when generating game levels, indicating their potential for enhancing PCG. In this presentation, I will share the results of comparing three metaheuristic algorithms (GA, PSO, and ABC) in map layout generation for game levels, emphasizing the potential benefits of leveraging diverse algorithmic approaches to create more captivating and immersive game worlds. Also, I will conclude with a call for further research in this area to expose new possibilities in content generation. By considering varied metaheuristic approaches, game developers can improve content generation techniques and create more captivating and interactive player experiences.

JAHAN: A framework for procedural generation of game maps from design specifications

Mobile learning and educational gaming are two trends that are rapidly having an increasing impact in Technology-Enhanced Learning. However, both approaches present significant technological challenges. Mobile technologies are very diverse and the market pressure pushes the continuous development of new technologies and features. On the other hand, game-based learning needs to deal with enormous development costs and the problem of allowing instructors and experts to actively participate in the game development process. Moreover, there are numerous situations where bringing both approaches together could be very useful, but this combination magnifies the technological barriers previously described. In this work we present <e-Adventure>, an authoring environment for educational adventure games that supports the production of both desktop and mobile games. This framework provides a graphical environment that allows instructors to create their own educational games with a low cost. Then, the games can be exported to multiple formats, including support for diverse types of mobile platforms. This is achieved through a modular semi-automated exportation process, which is based on mobile device profiles.

Clark’s (2013) prediction-action cognitive architecture predicts that active learners are more likely to learn. Even though this vision is widely spread in education, it has not been rigorously tested yet. This study investigated if agency while playing Mecanika, a serious educational game about Newtonian Physics knowledge, is beneficial to learning. Participants were 74 French-speaking undergraduate students with a novice background in Physics. Participants were paired and randomly designated as an active player or a passive watcher. Players played Mecanika for two hours while watchers were looking in real time on a separate screen a duplicate of the player’s screen. Dual-EEG was recorded to derive cognitive load and cognitive engagement metrics. Before and after the experiment, participants filled a Physics knowledge questionnaire, the Force Concept Inventory (Hestenes et al. 1992), where each of the five multiple choices for every item was either representing a scientific conception (good answer), and common misconceptions or fillers (wrong answers). Transitions occurring from pretest to posttest according to those three types of answers were analyzed. One unanticipated finding was that agency is less beneficial to learning than passively watching: watchers are more likely than players to transition from a wrong answer (either misconception of filler) to a good answer (scientific conception) between the pretest and the posttest. Statistical analyses of continuous psychophysiological measures of cognitive load and cognitive engagement didn’t show differences between players and watchers. Results point to a need for further research aiming at finer-grained decompositions of the performance and the learning context.

Making innovative, cohesive and appealing games has become inherently more difficult given the ever increasing competition in the digital games' market. Manually creating game content is expensive and time-consuming. Therefore, alternative approaches for game content creation are relevant for increasing the efficiency of the game development process. This is where procedural techniques step in. Even though they have been used by commercial games since the 1980s, it was only in recent years that this kind of approach has been given the righteous attention in the academic context. In this work, we propose a procedural content generation approach for creating infinite environments for a 2D platform runner game. The approach consists of a Genetic Algorithm that innovatively takes into account environment aesthetics as well as game's physics and rules in its fitness function. Therefore, the created environments should be pleasant and possible to be overcome by the player. An instantiation of the approach was developed using the Godot Game Engine. Time viability for in-game real-time generation and convergence to high/stable fitness values were experimentally evaluated. Our tests indicated parameter ranges that performed best in terms of environment quality and processing time were mutation rates between 0.5 % and 1 % aligned with a population ranging from 50 to 100 individuals. This approach is expandable to other games that have a tileman-based environments.

The Wave Function Collapse (WFC) algorithm is a widely used tile-based algorithm in procedural content generation, including textures, objects, and scenes. However, the current WFC algorithm and related optimized algorithms based on it lack the ability to generate commercial-scale or infinite content due to constraint conflicts and high time complexity. This paper proposes the Nested WFC (N-WFC) algorithm framework to reduce time complexity. To avoid conflict and backtracking problems, we offer a complete and sub-complete tileset preparation strategy, which requires only a small number of tiles to generate infinite, aperiodic, and deterministic content. We use Mario and Carcassonne as two game examples to describe their application and discuss potential research value. Our contribution addresses WFC's challenge in massive content generation and provides a theoretical basis for implementing concrete games.

It is well known that the use of Procedural Content Generation (PCG) techniques is commonly used in the digital gaming industry because of its efficiency in solving problems and consequently reducing development costs and time. In particular refers to a computer program that automate the game's content creation process, reducing the manual effort of human work. The choice of the technique also can be useful in other situations like compression of game data, save memory space, and others, but the implementation of the PCG technique requires a mastery over the problem that will be solved, because for each type of problem there is a type algorithm to be considered. The proposal of this research consists in the application of such technique for the automation of construction of characters and scripts for a serious game. The objective of this game is to convey educational content about skin lesions to primary care physicians. Within the game there are characters who are patients that have different phenotypes and skin blemishes, and the player must analyze if the stain contained in a patient is a cancer (melanoma), and subsequently decide if that patient should be referred to the dermatology sector or not. The implementation of the technique is based on generating these patients and the scripts with different peculiarities, taking into consideration the level of knowledge about the skin lesions that the player possesses to provide education and fun adapted to him. The results presented in this work are just tests of the implemented algorithms, but can be considered as in-game practical results, since the game was not tested with the main public yet.

This work presents TOAD-GAN (Token-based One-shot Arbitrary Dimension Generative Adversarial Network), a novel Procedural Content Generation (PCG) algorithm that generates token-based video game levels from only one example. We show that the created levels can be of arbitrary size, and the patterns of the training levels are well captured. The method can be extended with user interaction during the generation process to achieve certain token layouts and interpretations of the same base level by different generators. Our method is further evaluated with an extensive ablation study and level similarity metrics on the Super Mario Bros. benchmark. Finally, we extend our method to mix the style of multiple input levels, turning it into a framework for few-shot level generation.

Structural test data generation using a memetic ant colony optimization based on evolution strategies

We address the problem of automatically designing maps for first-person shooter (FPS) games. An efficient solution to this procedural content generation (PCG) problem could allow the design of FPS games of lower development cost with near-infinite replay value and capability to adapt to the skills and preferences of individual players. We propose a search-based solution, where maps are evolved to optimize a fitness function that is based on the players’ average fighting time. For that purpose, four different map representations are tested and compared. Results obtained showcase the clear advantage of some representations in generating interesting FPS maps and demonstrate the promise of the approach followed for automatic level design in that game genre.

Although there has been much work on procedural content generation for other game genres, very few researchers have tackled automated content generation for educational games. In this paper, we present a template-based, automatic puzzle generator for an educational puzzle programming game called BOTS. Two experts created their own new puzzles and evaluated generator-generated puzzles for meeting the educational goals, the structural and visual novelty. We show that our generator can generate puzzles with expert-designed educational goals while saving experts more than 80% of creation time, and these puzzles exhibit structural and visual novelty compared to expert-created puzzles. The contribution of this work is defined and implemented the first template-based automatic puzzle generator that saves expert time while incorporating expert-designed educational goals and enhancing puzzle.

This paper describes a domain independent approach to the use of genetic programming for object detection problems. Rather than using raw pixels or high level domain specific features, this approach uses domain independent statistical features as terminals in genetic programming. Besides position invariant statistics such as mean and standard deviation, this approach also uses position dependent pixel statistics such as moments and local region statistics as terminals. Based on an existing fitness function which uses linear combination of detection rate and alarm rate, we introduce a new measure called false alarm to the fitness function. In addition to the standard arithmetic operators, this approach also uses a conditional operator if in the function set. This approach is tested on two object detection problems. The experiments suggest that position dependent pixel statistics computed from local (central) regions and nonlinear condition functions are effective to object detection problems. Fitness functions with alarm area can reflect the smoothness of evolved genetic programs. This approach works well for the detecting small regular multiple class objects on a relatively uncluttered background.