The Pataphysic Institute (PI) is a research prototype multi-player game world. In PI, the personalities of the inhabitants are the base for the game mechanics. When interacting with other characters the potential emotional reactions depend upon avatars' current mood and personality. PI is built with inspiration from personality psychology and affect theory in an attempt to mimic possible emotional responses in order to give the player support in role-playing. The mental states of characters depend on their personalities and on their current moods. Moods differ according to context and to recent experiences. Emotional experiences become memories and define the relationships between characters. The mental state is the sum of the character and governs what actions can be performed in a given moment. In order to do certain things the characters need to be in certain moods — and for this the players need to game their avatars' emotions, and game their relationships.

An Alternate Reality Game (ARG) is an interactive narrative that uses the real world as a platform. An ARG layers a fictional world over the real world such that, as a player moves through the real world, a narrative structure plays out. Although ARGs are growing in popularity, they are significantly limited in several ways that prevent ARGs from being utilized by mainstream game players. First, there is a substantial cost in running an ARG, limiting the number of players that can participate in an ARG at any given time. Second, ARG storylines reference real world geographical locations and landmarks in the real world to advance the narrative structure. In this paper, we introduce a suite of technologies designed to overcome scalability issues of ARGs by automating the delivery of the game and by encouraging end-user authoring of new location-specific storylines.

From subtle political intrigue to outright physical combat, conflict is essential to interesting stories. Narratology research emphasizes that conflict provides structure and engagement, so narrative systems stand to benefit greatly from a computational model of this phenomenon. We present such a model based on AI planing, along with formulas for measuring seven essential properties: participants, subject, duration, directness, intensity, balance, and resolution. We also sketch an algorithm which uses this model to create stories structured around a central struggle.

As game designers shift focus from graphical realism to immersive stories, the number of game-object interactions grows exponentially. Games use manually written scripts to control interactions. ScriptEase provides game designers with generative patterns that generate scripting code to control common interactions. This paper describes a new kind of generative pattern, quest patterns, that generate scripting code to control story plot. We present our quest pattern architecture and study results that show quest patterns are easy-to-use and reduce plot scripting errors.

In the context of interactive, virtual experiences, the use of personality models to maintain consistent character behaviour is becoming more widespread in both industry and academia. Most current techniques, however, are limited in one of three ways: either they overly restrict user actions, have a high cost for creating varied content, or rely on a representation that prohibits conveying complex content to the user.  Toward addressing these issues, we introduce Socially Consistent Role Passing, a mechanism for ensuring consistent character behaviour that leverages the design of PaSSAGE, an existing system for generating adaptive, interactive stories.  While results from previous human user studies have shown that PaSSAGE improves the enjoyment of players with little gaming experience, we present results from a new study showing that PaSSAGE's adaptive stories, augmented with Socially Consistent Role Passing, improve the enjoyment of all players versus a set of fixed-structure alternatives.

The first major story generation system, which preceded Minstrel and which While ongoing progress in digital entertainment also received significant attention, is Tale-Spin (Meehan technology continues, commercial designers still largely 1977). Like Minstrel, this system generates stories which eschew systems for procedural story generation, preferring satisfy user-submitted requirements. Tale-Spin creates instead to generate content by hand. In the academic English stories by planning a method for the main literature, projects such as (Appling & Riedl 2009, Roberts character to achieve her or his goal, using inferences and & Isbell 2009) continue to investigate ways to improve the rules to generate a large number of details about a story nuances of interactive storytelling while others attempt to (many of which do little contribute to an audience create their own systems to investigate ways to use experience). This contrasts nicely with Minstrel, which knowledge from interactive narrative and story generation performs no logical inferences and which performs all in new fields such as playable games (Drachen & Hitchens actions from the point of view of an author, manipulating et al. 2009, Sullivan, Mateas & Wardrip-Fruin 2009).

This paper proposes an automatic model-based approach that enables adaptive decision making in modern virtual games. It builds upon the Integrated MDP and POMDP Learning AgeNT (IMPLANT) architecture which has shown to provide plausible adaptive decision making in modern games. However, it suffers from highly time-consuming manual model specification problems. By incorporating an automated priority sweeping based model builder for the MDP, as well as using the Tactical Agent Personality for the POMDP, the work in this paper aims to resolve these problems. Empirical proof of concept is shown based on an implementation in a modern game scenario, whereby the enhanced IMPLANT agent is shown to exhibit superior adaptation performance over the old IMPLANT agent whilst eliminating manual model specifications and at the same time still maintaining plausible speeds.

This research aims at building a preference-based player model of Civilization IV players. Our model incorporates attributes which are defined for AI players. We use a sequential minimal optimization (SMO) classifier to build the player model based on a training set with observations of a large number of games between six AI players. The model was validated on a test set of games between the same six AI players. While it did not seem to generalize well to the preferences of different AI players, it did manage to accurately predict some of the preferences for a veteran human player. Further tests showed that AI players with the same play styles but different preference values were often confused by the model. We conclude that for a complex game such as Civilization IV a model that attempts to accurately predict specific preference values is hard to construct. A model that focusses on play styles might succeed better.

Story Canvas is a visual authoring tool for the creation of interactive, generative stories. Aimed at authors without a technical background in computational storytelling, our system takes an existing author goal-based narrative planning architecture and adds a highly visual authoring and reading interface to the technology, using the language of storyboards and comics as a framework for both authoring and interacting with the resulting narratives. In this paper we describe Story Canvas and its evolution from our previous authoring work, including how our interface choices have been driven by our previous experiences with non-technical authors, and describe the details of translating the visual authoring constructs into story plans within the story generator.

Autonomous agents in real-time strategy (RTS) games lack an integrated framework for reasoning about choke points and regions of open space in their environment. This paper presents an algorithm which partitions the environment into a set of polygonal regions and computes optimal choke points between adjacent regions. This representation can be used as a component for AI agents to reason about terrain, plan multiple routes of attack, and make other tactical decisions. The algorithm is tested on a set of popular maps commonly used in international Starcraft competitions and evaluated against answers made by human participants. The algorithm identified 97% of the choke points that the participants found and also identified a number of bottlenecks that human participants did not recognize as choke points.