Game designers can use computer-aided game design methods to quantitatively compare player skill levels, different game variants, and learning rates, for the purpose of modeling how players will likely experience a game. We use Monte-Carlo simulation, hazard functions, and survival analysis to show how difficulty will quantitatively change throughout a game level as we vary skill, game parameters, and learning rates. We give a mathematical overview of survival analysis, present empirical data analyses of our player models for each game variant, and provide theoretical probability distributions for each game. This analysis shows the quantitative reasons why balancing a game for a wide range of player skill can be difficult; our player modeling provides tools for tuning this game balance. We also analyze the score distribution of over 175 million play sessions of a popular online Flappy Bird variant to demonstrate how learning effects can impact scores, implying that learning is crucial aspect of player modeling.

Is it possible to conduct player modeling without any players? In this paper we use Monte-Carlo Tree Search-controlled procedural personas to simulate a range of decision making styles in the puzzle game MiniDungeons 2. The purpose is to provide a method for synthetic play testing of game levels with synthetic players based on designer intuition and experience. Five personas are constructed, representing five different decision making styles archetypal for the game. The personas vary solely in the weights of decision-making utilities that describe their valuation of a set affordances in MiniDungeons 2. By configuring these weights using designer expert knowledge, and passing the configurations directly to the MCTS algorithm, we make the personas exhibit a number of distinct decision making and play styles.

Non-player characters in games generally lack believability and deep interactivity. The AI system Comme il Faut begins to tackle this by modeling social state and behaviors for game characters. The player initiates social exchanges and the dialog and outcome are generated and displayed in their entirety. In this paper we present a model called social prac-tices to extend Comme il Faut. Social practices increase the playability of social play by modeling social interactions at a more granular level and adding interactivity at each stage. This model also moves away from dialog trees to a more modular form of authoring to support the additional com-plexity.

An integral part of social believability in role playing games is believability of non-player characters (NPC). In this paper we argue for the importance of believability in NPCs, even those that are completely outside of any pre-written quest or plot. We present NPCAgency, a system designed to generate many conversational NPCs as packaged narrative assets that can be shared and imported into various projects to increase story-world immersion. We believe such a system can help solve two problems. First, the authorial burden of the game designer is lessened, allowing renderings of large numbers of NPCs, each with their own unique background and conversation topics, all conforming to the norms of a predefined “universe”. Second, the immersive aspect of the game is heightened as the player can engage complex characters with lengthy dialogue affordances. We demonstrate the concept by generating fifty characters with attributes drawn from “Game of Thrones” (GOT) / “A Song of Ice and Fire” universe, and exporting them as Inform 7 code, a popular declarative interactive fiction (IF) programming language and authoring tool. A user study of thirty-seven Inform 7 programmers demonstrates that a 62% majority find the tool useful enough to consider for their own work. Further 70% said they would use the system to create “Game of Thrones” background characters for their own projects.

Previous research demonstrates that social experience is a key motivation for continued play in online games. We argue that there is an untapped potential for NPCs to act as social mediators in online games by stimulating social interaction between players. For example, a social mediator NPC could ask in chat, “How is everyone’s day?” to encourage conversations between players. We suggest two potential applications for social mediator NPCs in online games by examining social experiences in two contemporary massively-multiplayer online role-playing games (MMOs): Guild Wars 2 and World of Warcraft.

Believability requires video game characters to consider their actions within the context of social norms. Social norms involve a broad range of behavioral defaults, obligations, and injunctions unrelated to strictly causal reasoning.  Defeasible reasoning involves rationally compelling but deductively invalid arguments, such as reasoning with rules that allow exceptions. This paper investigates having video game characters use defeasible reasoning to consider injunctive social norms when selecting and planning actions.

Culturally appropriate behavior is not genetically programmed, but is instead learned from direct teaching, or by The relevant literature maintains many different definitions observing and interacting with others. For example, language of culture, which vary according to the field of study. Hofstede is one of the primary abstract artifacts transmitted has studied the features that allow us to discern different extra genetically. This paper provides a review of how culturally cultures (Hofstede 2001), defining culture as: appropriate behavior can be achieved in synthetic agents and offers a concise overview of the relevant literature. "The collective programming of the mind that distinguishes the members of one group or category of people Bates (1994) describes believable characters as those from another" (Hofstede 2001, page 9).

We have constructed a system that supports unscripted social interaction between a player and virtual characters, where the participants pursue internal agendas and respond to one another in real-time.  Our emphasis on unscripted interaction means that the characters must accept dynamically generated performance requests, while our concern with social interaction implies that the characters must interleave performances with an attention to natural flow that encourages social engagement. We present initial work on a performance management mechanism that produces this interleaving.   It initiates and suspends character performances by allocating animation resources to requests via a utility function representing aesthetic concerns.  That function weighs extrinsic factors reflecting the purpose of taking an action against intrinsic ones that concern features of a given performance.  We show, via multiple short videos, that the features are individually material to the aesthetic quality of the result and that the mechanism can produce aesthetically pleasing performances on par with the best hand-generated prioritization scheme. We argue, anecdotally, that the parameters of the model are easy to identify, suggesting that the feature vocabulary is both intuitive and useful for shaping character performances.

Natural language generation (NLG) has been featured in at most a handful of shipped games and interactive stories. This is certainly due to it being a very specialized practice, but another contributing factor is that the state of the art today, in terms of content quality, is simply inadequate. The major benefits of NLG are its alleviation of authorial burden and the capability it gives to a system of generating state-bespoke content, but we believe we can have these benefits without actually employing a full NLG pipeline. In this paper, we present the preliminary design of Expressionist, an in-development mixed-initiative authoring tool that instantiates an authoring scheme residing somewhere between conventional NLG and conventional human content authoring. In this scheme, a human author plays the part of an NLG module in that she starts from a set of deep representations constructed for the game or story domain and proceeds to specify dialogic content that may express those representations. Rather than authoring static dialogue, the author defines a probabilistic context-free grammar that yields templated dialogue. This allows a human author to still harness a computer's generativity, but in a capacity in which it can be trusted: operating over probabilities and treelike control structures. Additional features of Expressionist's design include arbitrary markup and realtime feedback showing currently valid derivations.

In order to use computational intelligence for automated narrative synthesis, domain knowledge of the story world must be defined, a task which is currently confined to experts. This paper discusses the benefits and tradeoffs between agent-centric and event-centric approaches towards authoring the domain knowledge of story worlds. In an effort to democratize story world creation, we present an accessible graphical platform for content creators and even end users to create their own story worlds, populate it with smart characters and objects, and define narrative events that can be used by existing tools for automated narrative synthesis. We demonstrate the potential of our system by authoring a simple bank robbery story world, and integrate it with existing solutions for event-centric planning to synthesize example digital stories.