This survey explores Procedural Content Generation via Machine Learning (PCGML), defined as the generation of game content using machine learning models trained on existing content. As the importance of PCG for game development increases, researchers explore new avenues for generating high-quality content with or without human involvement; this paper addresses the relatively new paradigm of using machine learning (in contrast with search-based, solver-based, and constructive methods). We focus on what is most often considered functional game content such as platformer levels, game maps, interactive fiction stories, and cards in collectible card games, as opposed to cosmetic content such as sprites and sound effects. In addition to using PCG for autonomous generation, co-creativity, mixed-initiative design, and compression, PCGML is suited for repair, critique, and content analysis because of its focus on modeling existing content. We discuss various data sources and representations that affect the generated content. Multiple PCGML methods are covered, including neural networks: long short-term memory (LSTM) networks, autoencoders, and deep convolutional networks; Markov models: n-grams and multi-dimensional Markov chains; clustering; and matrix factorization. Finally, we discuss open problems in PCGML, including learning from small datasets, lack of training data, multi-layered learning, style-transfer, parameter tuning, and PCG as a game mechanic.
This paper describes a method for generative player modeling and its application to the automatic testing of game content using archetypal player models called procedural personas. Theoretically grounded in psychological decision theory, procedural personas are implemented using a variation of Monte Carlo Tree Search (MCTS) where the node selection criteria are developed using evolutionary computation, replacing the standard UCB1 criterion of MCTS. Using these personas we demonstrate how generative player models can be applied to a varied corpus of game levels and demonstrate how different play styles can be enacted in each level. In short, we use artificially intelligent personas to construct synthetic playtesters. The proposed approach could be used as a tool for automatic play testing when human feedback is not readily available or when quick visualization of potential interactions is necessary. Possible applications include interactive tools during game development or procedural content generation systems where many evaluations must be conducted within a short time span.
Abstract-This paper explores how evolved game playing agents can be used to represent a priori defined archetypical ways of playing a test-bed game, as procedural personas. The end goal of such procedural personas is substituting players when authoring game content manually, procedurally, or both (in a mixed-initiative setting). Building on previous work, we compare the performance of newly evolved agents to agents trained via Q-learning as well as a number of baseline agents. Comparisons are performed on the grounds of game playing ability, generalizability, and conformity among agents. Finally, all agents' decision making styles are matched to the decision making styles of human players in order to investigate whether the different methods can yield agents who mimic or differ from human decision making in similar ways. The experiments performed in this paper conclude that agents developed from a priori defined objectives can express human decision making styles and that they are more generalizable and versatile than Q-learning and hand-crafted agents.
Abstract. This paper introduces a constrained optimization method which uses procedural personas to evaluate the playability and quality of evolved dungeon levels. Procedural personas represent archetypical player behaviors, and their controllers have been evolved to maximize a specific utility which drives their decisions. A "baseline" persona evaluates whether a level is playable by testing if it can survive in a worst-case scenario of the playthrough. On the other hand, a Monster Killer persona or a Treasure Collector persona evaluates playable levels based on how many monsters it can kill or how many treasures it can collect, respectively. Results show that the implemented two-population genetic algorithm discovers playable levels quickly and reliably, while the different personas affect the layout, difficulty level and tactical depth of the generated dungeons.
No abstract
Jumping has been an important mechanic since its introduction in Donkey Kong. It has taken a variety of forms and shown up in numerous games, with each jump having a di erent feel. In this paper, we use a modi ed Nintendo Entertainment System (NES) emulator to semi-automatically run experiments on a large subset (∼30%) of NES platform games. We use these experiments to build models of jumps from di erent developers, series, and games across the history of the console. We then examine these models to gain insights into di erent forms of jumping and their associated feel.
Computer games have recently shown promise as a diagnostic and treatment tool for psychiatric rehabilitation. This paper examines the positive impact of affect detection and advanced game technology on the treatment of mental diagnoses such as Post Traumatic Stress Disorder (PTSD). For that purpose, we couple game design and game technology with stress detection for the automatic profiling and the personalized treatment of PTSD via game-based exposure therapy and stress inoculation training. The PTSD treatment game we designed forces the player to go through various stressful experiences while a stress detection mechanism profiles the severity and type of PTSD via skin conductance responses to those in-game stress elicitors. The initial study and analysis of 14 PTSD-diagnosed veteran soldiers presented in this paper reveals clear correspondence between diagnostic standard measures of PTSD severity and skin conductance responses. Significant correlations between physiological responses and subjective evaluations of the stressfulness of experiences, represented as pairwise preferences, are also found. We conclude that this supports the use of the simulation as a relevant treatment tool for stress inoculation training. This points to future avenues of research toward discerning between degrees and types of PTSD using game-based diagnostic and treatment tools.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.