• Game_Technology
• Lopes

Generation of adaptive game worlds

Ricardo Lopes

Typically, when most commercial games and simulations are shipped, their gameplay is already pre-scripted. Game content, rules, narratives and environments are created during development, mostly as static elements with which a dynamic player will interact. Designing such predefined content is standard because it allows games and simulations to remain robust, testable and controllable. As a result of such rigidity, game outcomes can be more fairly anticipated by players, since all possible interactions are bounded by such static elements. Even worse, if players can predict certain outcomes, their progress can be often achieved by repeatedly exploiting a successful strategy.

In an attempt to account for player individuality, games and simulations often include minor variations that depend on players profiling themselves. For example, by customizing the difficulty level or choosing time constraints, players are classifying themselves as one of the available pre-defined low-resolution stereotypes (e.g. beginners, experts). However, this discrete approach implies that such games might fail in appealing to players who do not know how to profile themselves or who do not identify themselves with any of the available classifications.

Static game content and its pre-defined variations (based on low resolution profiles), all can lead to games and simulations that can be played in an impersonal, predictable and inflexible fashion and that can fail to appeal to broader audiences.

To solve the above shortcomings, many researchers agree that games and simulations have to become more challenging, unpredictable and player-centric, catering the gaming experience to the individual user and being more responsive to different individual needs. Player-centered game adaptivity can help to accomplish these goals.

The main research goal of this PhD project is to create methods to support the on-line generation of adaptive game worlds, i.e. which fit the player performance and expected gameplay experience. For example, recognizing a runtime requirement for the increase or decrease of fun, for a particular player, should result in the generation of new content (or the adjustment of existing one) that materializes that specific personal requirement. Researched methods will contribute towards adaptivity in games, by providing a more complete and structured generation process to be integrated with player (experience) modeling techniques.

To achieve this main goal, this PhD research aims at:

• enabling the generation of customized game worlds that, although stochastically based, is procedurally determined by player-dependent data;
• facilitating the re-usability of the new generation methods with different player and experience modeling methods;
• exploring new research on semantic modeling, introducing appropriate semantics about players and their gameplay;
• enabling game designers to control the generation process and therefore author adaptivity;
• investigating new performance-driven techniques to support a generation process that can perform optimally at runtime.

This research project aims at encouraging games and simulations to become more flexible, agile and complete in their ways to adapt to the player. A better adaptivity has the potential to make games and simulations even more unpredictable, effective and fun.

For publications from this project, please check here

News