<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>OAR@UM Collection:</title>
    <link>https://www.um.edu.mt/library/oar/handle/123456789/70138</link>
    <description />
    <pubDate>Sun, 05 Apr 2026 17:10:27 GMT</pubDate>
    <dc:date>2026-04-05T17:10:27Z</dc:date>
    <item>
      <title>Orchestrating the generation of game facets via a model of gameplay</title>
      <link>https://www.um.edu.mt/library/oar/handle/123456789/70321</link>
      <description>Title: Orchestrating the generation of game facets via a model of gameplay
Abstract: Computer games are media that weave together many different facets. When&#xD;
the design of games is supported by the automatic creation of game content, a&#xD;
multidisciplinary approach would be expected. Yet, many approaches to procedural content generation tend to focus on a single facet at a time, assuming that&#xD;
a human game designer will guarantee a suitable context. The systems that do&#xD;
create multiple types of content usually rely on expensive game simulations to&#xD;
evaluate their quality and complementarity. However, the complexity of modern&#xD;
games increases the runtime of these simulations to such a degree that at some&#xD;
point this approach becomes infeasible.&#xD;
This thesis proposes a framework for the procedural generation of the level&#xD;
and ruleset components of games via a model of gameplay that can act as a&#xD;
surrogate for expensive game simulations. By combining the level and ruleset&#xD;
components as input and gameplay outcomes as output, deep learning is used&#xD;
to construct a mapping between three different facets of a game. This thesis&#xD;
argues that the learned mapping enables the model to identify the synergies&#xD;
between these facets, which can be used to orchestrate the generation of both&#xD;
level and rules towards desired gameplay outcomes. The experiments support&#xD;
this by demonstrating the ability of a search-based generative approach that&#xD;
uses a surrogate model for quality evaluation to adapt players’ character classes,&#xD;
levels, or both towards designer-specified targets in the domain of shooter games.&#xD;
The findings demonstrate that the proposed method of game facet orchestration&#xD;
can produce improved designs of both facets without the use of simulations and&#xD;
makes less changes to an initial design than traditional single-facet methods.
Description: PH.D.</description>
      <pubDate>Wed, 01 Jan 2020 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">https://www.um.edu.mt/library/oar/handle/123456789/70321</guid>
      <dc:date>2020-01-01T00:00:00Z</dc:date>
    </item>
  </channel>
</rss>

