Multi-agent planning for interactive emergent narrative systems

It appears your Web browser is not configured to display PDF files. Download adobe Acrobat or click here to download the PDF file.

Click here to download the PDF file.


Breault, Vincent




Generation of narrative is a domain that is mostly exclusive to human authors. Most current narrative generators use planning to adapt or follow a human authored story or guideline. This work proposes an engine for Creation Of Novel Adventure Narrative (CONAN). It uses a procedural approach to story generation that uses series of quests to make a rich player – NPC (non-player character) interaction from which a structured narrative can emerge. The engine is tested on its ability to create quests, which are sets of actions that must be performed in order to achieve a certain goal, usually for
a reward. Compared against human structural quest analysis, the current engine was found to be able to replicate the structure found in commercial video game quests.


Computer Science
Artificial Intelligence




Carleton University

Thesis Degree Name: 

Master of Cognitive Science: 

Thesis Degree Level: 


Thesis Degree Discipline: 

Cognitive Science

Parent Collection: 

Theses and Dissertations

Items in CURVE are protected by copyright, with all rights reserved, unless otherwise indicated. They are made available with permission from the author(s).