Most computer game characters are either ``talkers,' i.e., they engage in dialogue with the player, or ``fighters,' i.e., they engage in actions against or with the player, and that may affect the virtual world. The reason for this dichotomy is a corresponding gap in the underlying development technologies used for each kind of character. Using concepts from task modeling and computational linguistics, we have developed a new kind of character-authoring technology which bridges this gap, thereby making it possible to create richer and more interesting characters for computer games.

Procedural Content Generation (PCG) has become one of the hottest topics in Computational Intelligence and Artificial Intelligence (AI) game research in the past few years. PCG is the process of automatically creating content for video games, rather than by hand, and can offer great benefits for video games companies by helping to bring costs down and quality up. By guiding the process with AI it can be enhanced further and even be made to personalize content for target players. Among the current research into PCG, search-based approaches overwhelmingly dominate. While search-based algorithms have been shown to have great promise and produce several success stories there are a number of open challenges remaining. In this thesis, we present the Learning-Based Procedural Content Generation (LBPCG) framework, which is an alternative, novel approach designed to address some of these challenges. The major difference between the LBPCG framework and contemporary approaches is that the LBPCG is designed to learn about the problem space, freeing itself from the necessity for hard-coded information by the game developers. In this thesis we apply the LBPCG to a concrete example, the classic first-person shooter Quake, and present results showing the potential of the framework in generating quality content.

Open-world video games give players a large environment to explore along with increased freedom to navigate and manipulate that environment. These requirements pose several problems that must be addressed by a game's graphics engine. Often there are a large number of visible objects, such as all of the trees in a forest, as well as objects comprised of large amounts of geometry, such as terrain. An open-world graphics engine must be able to render large environments at varying levels of detail and smoothly transition between detail levels to provide a believable experience. Often this involves finding a way to both store and generate the large amounts of geometry that represent the environment. In this thesis we present a system for generating and rendering large exterior environments, with a focus on terrain and vegetation. We use a region-based procedural generation algorithm to create environments of varying types. This algorithm produces content that can be rendered at multiple levels of detail. The terrain is rendered volumetrically to support caves, overhangs, and cliffs, but is also rendered using heightmaps to allow for large view distances. Vegetation is implemented using procedurally generated meshes and impostors. The volumetric terrain is editable in real time, which limits our ability to pre-generate or cache large amounts of geometry, and also limits the number of assumptions we can make with regard to visibility. We support a view distance of at least 25 miles in each direction, though distant objects are rendered at low resolution. The heightmap terrain used to achieve this view distance consists of over 360,000 triangles. Our system runs at 180 frames per second on commodity desktop hardware.

Die Arbeit bildet einen Einstieg in das Themengebiet der prozeduralen Karten Generierung mit Cellular Automata und verweist auf fortführende Möglichkeiten. Es wird gezeigt, wie eine zwei-dimensionale und hexagonale Terrain-Karte für Strategiespiele mit Cellular Automata erzeugt werden kann. Dazu wird eine allgemeine Einführung zu zellulären Automaten gegeben. Zusätzlich werden Fashion-based Cellular Automata und Cellular Automata mit mehreren aktiven Zellen erklärt. Es werden die Anforderungen an eine Karte des Strategie-Genres bestimmt, wobei der Fokus, auf dem durch Civilisation definierten Sub-Genre liegt. Anschließend wird gezeigt, wie die verschiedenen Bestandteile der Karte jeweils mit einem Cellular Automaton generiert werden können. Zu diesen werden Vorteile und Nachteile dargestellt und dabei auf die Performance eingegangen. Es zeigt sich das zelluläre Automaten in der Lage sind eine geeignete Karte zu erzeugen.:1 Einleitung 1.1 Videospiele im Trend 1.2 Produktionsaufwand 1.3 Prozedurale Content Generierung 1.4 Cellular Automata 1.5 Kartengenerierung 1.6 Aufbau der Arbeit 1.7 Verwendete Werkzeuge 2 Hintergrund 2.1 Cellular Automata 2.1.1 Grundsätze 2.1.2 Initiale globale Konfiguration eines CA 2.1.3 CA-Ansätze 2.1.3.1 Lattice Gases 2.1.3.2 CA mit mehreren aktiven Zellen 2.1.3.3 Fashion-based 3 Anforderungsanalyse 3.1 Eingrenzung der Karte 3.2 Betrachtete Spiele 3.3 Analyse der Karten 3.4 Anforderungen 4 Implementierung 4.1 Schichtenmodell 4.1.1 Regionen 4.1.1.1 Ansatz 4.1.1.2 Resultat 4.1.2 Höhenstufen 4.1.2.1 Ansatz 4.1.2.2 Resultat 4.1.3 Flüsse 4.1.3.1 Initiale Konfiguration 4.1.3.2 Flussrichtung 4.1.3.3 Resultat 4.1.4 Ressourcen 4.1.4.1 Wälder 4.1.4.2 Allgemeine Ressourcen 4.1.4.3 Siedlungen 4.1.5 Dynamische Veränderungen 4.1.6 Performance 5 Fazit 5.1 Ausblick 6 Verzeichnisse 6.1 Literaturverzeichnis 6.2 Abbildungsverzeichnis 6.3 Tabellenverzeichnis

No description available.

The goal of this work is to create a generator that provides a corpora of input episodes in the specified format, which can be used as an input to test episodic memory models. More specifically, the methods used should ensure the scope to be in years up to a possible lifetime of a typical human agent. It also attempts to verify this on an actual episodic memory model, and test if the generated data has high enough quality to be used for testing psychological paradigms on memory models.

Detta arbete handlar om Procedural Content Generation (PCG) i form av algoritmer som skapar osymmetriska banor och fokuserar på att ge en översikt av prestanda avseende tid, storlek samt tillgänglighetsgaranti. Tre olika algoritmer testades på hur lång tid det tog att skapa en bana, hur stora dess banor blev och om dessa banor tillåter att man kan nå alla gängliga områden. En Agentbaserad algoritm, Cellular Automata och Diffusion-limited Aggregation (DLA) studerades avseende dess styrkor och svagheter. Efter experimentet så drogs slutsatsen att DLA var mest effektiv inom tid och garanti dock skapade den små banor. Cellular Automata lyckades skapa stora rum men kunde de inte godkännas på punkten garanti, och den tog för lång tid att köra. Den Agentbaserade algoritmen misslyckades att skapa banor överhuvudtaget.

Detta arbete handlar om Procedural Content Generation (PCG) i form av algoritmer som skapar osymmetriska banor, och fokuserar på att ge en översikt av prestanda avseende tid, storlek och tillgänglighetsgaranti. Tre olika algoritmer testades på hur lång tid det tog att skapa en bana, och hur stora dess banor blev, och om dessa banor tillåter att man kan nå alla gängliga områden. En Agentbaserad algoritm, Cellular Automata och Diffusion-limited Aggregation (DLA) studerades avseende dess styrkor och svagheter. Efter experimentet så drogs slutsatsen att DLA var mest effektiv inom tid och garanti dock skapade den små banor. Cellular Automata lyckades skapa stora rum men kunde de inte godkännas på punkten garanti, och den tog för lång tid att köra. Den Agentbaserade algoritmen misslyckades att skapa banor överhuvudtaget.

Procedural Content Generation innebär att spelinnehåll genereras automatiskt för att dels minska arbetsbelastningen hos designers men också för att öka variationen i spel. Ett användningsområde för detta är rumsbaserad bangenerering där banor byggs upp av fördefinierade rum. Målet med det här arbetet var att implementera och jämföra tre olika algoritmer som kan åstadkomma detta; Binary Space Partitioning, Shortest path och en evolutionär algoritm. De kriterier som algoritmerna utvärderades på var tidseffektivitet, variation och möjligheten att nå alla rum. Resultatet visade att Binary Space Partitioning och Shortest path var de två algoritmer som var bäst lämpade att användas i ett spel där genereringen ska ske under körtiden. Detta eftersom de genererade banor förhållandevis snabbt och av god kvalitet. Om arbetet skulle fortsätta i framtiden skulle det vara intressant att utföra fler tester med fler olika värden samt använda algoritmerna i ett spel och sedan låta spelare bedöma banorna som genereras.

Role-playing games (RPGs) rely on interesting and varied experiences to maintain player attention. These experiences are often provided through quests, which give players tasks that are used to advance stories or events unfolding in the game. Traditional quests in video games require very specific conditions to be met, and for participating members to advance them by carrying out pre-defined actions. These types of quests are generated with perfect knowledge of the game world and are able to force desired behaviors out of the relevant non-player characters (NPCs). This becomes a major issue in massive multiplayer online (MMO) when other players can often disrupt the conditions needed for quests to unfold in a believable and immersive way, leading to the absence of a genuine multiplayer RPG experience. Our proposed solution is to dynamically create quests from real-time information on the unscripted actions of other NPCs and players in a game. This thesis shows that it is possible to create logical quests without global information knowledge, pre-defined story-trees, or prescribed player and NPC behavior. This allows players to become involved in storylines without having to perform any specific actions. Results are shown through a game scenario created from the Panoptyk Engine, a game engine in early development designed to test AI reasoning with information and the removal of the distinction between NPC and human players. We focus on quests issued by the NPC faction leaders of several in-game groups known as factions. Our generated quests are created logically from the pre-defined personality of each NPC leader, their memory of previous events, and information given to them by in-game sources. Long-spanning conflicts are seen to emerge from factions issuing quests against each other; these conflicts can be represented in a coherent narrative. A user study shows that players felt quests were logical, that players were able to recognize quests were based on events happening in the game, and that players experienced follow-up consequences from their actions in quests.