Una metodología de ajuste dinámico de dificultad en videojuegos : entre Rubber Band AI y la teoría de flow
Loading...
Download
Official URL
Full text at PDC
Publication date
2023
Defense date
18/07/2022
Authors
Advisors (or tutors)
Editors
Journal Title
Journal ISSN
Volume Title
Publisher
Universidad Complutense de Madrid
Citation
Abstract
Uno de los desafíos más relevantes durante la producción de videojuegos es la creación de retos adecuados para los jugadores. Normalmente, la producción de un videojuego AAA toma aproximadamente 2 años y la razón principal es que las ideas que se quieren desarrollar deben ser probadas, no solo para encontrar errores en el código, sino también para validar que sean entretenidas y factibles. Este trabajo tiene como objetivo crear una metodología que facilite el establecimiento de retos adecuados empleando ajuste dinámico de dificultad en videojuegos. Después de revisar la literatura sobre el modelado de jugadores y el ajuste dinámico de dificultad, realizamos varios experimentos donde los participantes jugaron diversas versiones de Tetris. La versión que implementaba la metodología propuesta predecía el nivel de habilidad del jugador actual extrayendo los datos de sus últimas acciones y comparaba la evolución de la partida con partidas de otros jugadores. Luego, decidía si se modificaba la dificultad del juego teniendo en cuenta el nivel de habilidad previamente calculado. Usamos dos enfoques de ajuste dinámico de dificultad, el Ruber Band AI y la teoría del flow, para implementar las diversas versiones de Tetris. Además, los participantes respondieron cuestionarios con el fin de conocer qué tan satisfactoria fue su experiencia en cada sesión...
One of the most relevant challenges during the video games production is the creation of adequate challenges for the players. Normally, the production of an AAA video game takes approximately 2 years and the main reason is that the ideas to be deveoped must be tested, not only to find bugs in the code, but also to validate that these are entertaining and geasible. This work aims to create a methodology that facilitates the establishment of appropriate challenges using dynamic difficulty adjustment in video games. After reviewing the literature on playre modelling and dynamic difficulty adjustment, we conducted several experiments where participants played different versions of Tetris. The version that implemented the proposed methodology predicted the current player's skill level by extracting data from his last actions and compared the evolution of the game with other player's games. Then, it decided ehether to modify the game's difficulty by considering the previously calculated skill level. We used two dynamic difficulty adjustment approaches, the Rubber Band AI and the flow theory, to implement the various versions of Tetris. In addition, participants answered questionnaires to identify if their experience was satisfactory in each session...
One of the most relevant challenges during the video games production is the creation of adequate challenges for the players. Normally, the production of an AAA video game takes approximately 2 years and the main reason is that the ideas to be deveoped must be tested, not only to find bugs in the code, but also to validate that these are entertaining and geasible. This work aims to create a methodology that facilitates the establishment of appropriate challenges using dynamic difficulty adjustment in video games. After reviewing the literature on playre modelling and dynamic difficulty adjustment, we conducted several experiments where participants played different versions of Tetris. The version that implemented the proposed methodology predicted the current player's skill level by extracting data from his last actions and compared the evolution of the game with other player's games. Then, it decided ehether to modify the game's difficulty by considering the previously calculated skill level. We used two dynamic difficulty adjustment approaches, the Rubber Band AI and the flow theory, to implement the various versions of Tetris. In addition, participants answered questionnaires to identify if their experience was satisfactory in each session...
Description
Tesis inédita de la Universidad Complutense de Madrid, Facultad de Informática, Departamento de Ingeniería del Software e Inteligencia Artificial, leída el 18-07-2022