We propose the creation of computational caricatures as a design research practice that aims to advance understanding of the game design process and to develop the reusable technology for design automation. Computational caricatures capture and exaggerate statements about the game design process in the form of computational systems (i.e. software and hardware). In comparison with empirical interviews of game designers, arguments from established design theory, and the creation of neutral simulations of the design process, computational caricatures provide more direct access to inquiry and insight about design. Further, they tangibly demonstrate architectures and subsystems for a new generation of human-assisting design support systems and adaptive games that embed aspects of automated design in their runtime processes. In this paper, we frame the idea of computational caricature, review several existing design automation prototypes through the lens of caricature, and call for more design research to be done following this practice.

In this work, we look at the challenge of learning in an action game,Infinite Mario. Learning to play an action game can be divided intotwo distinct but related problems, learning an object-relatedbehavior and selecting a primitive action. We propose a framework that allows for the use of reinforcement learning for both ofthese problems. We present promising results in some instances of thegame and identify some problems that might affect learning.

In this paper, we discuss approaches to dialogue in interactive video games and interactive narrative research. We propose that situating interactive dialogue in the simplified expectations of video games is a profitable way to investigate computational dialogue simulation. Taking cues from existing physical simulations such as combat, we propose a hypothetical game environment and design goals for an embedded interactive dialogue system. We present a modular framework targeted at that environment, which is designed to enable incremental development and exploration of dialogue concepts. We describe this framework together with a work-in-progress system for simulating simple in-game negotiation dialogues.

Meaningful choice has often been identified as a key component in a player's engagement with an interactive narrative, but branching stories require tremendous amounts of hand-authored content, in amounts that increase exponentially rather than linearly as more choice points are added. Previous approaches to reducing authorial burden for computer RPGs have relied on creating better tools to manage existing unwieldy structures of quests and dialogue trees. We hypothesize that reducing authorial burden and increasing agency are two sides of the same coin, requiring specific advancements in two related areas of design and technology research: (1) dynamic story management architecture that represents story events abstractly and allows story elements to be selected and re-ordered in response to player choices, and (2) dynamic dialogue generation to allow a single story event to be revealed differently by different characters and in the context of dynamic relationships between those characters and the player. This paper describes SpyFeet, a playable prototype of a storytellingsystem designed to test this hypothesis.

We apply decision theoretic techniques to construct non-player characters that are able to assist a human player in collaborative games. The method is based on solving Markov decision processes, which can be difficult when the game state is described by many variables. To scale to more complex games, the method allows decomposition of a game task into subtasks, each of which can be modelled by a Markov decision process. Intention recognition is used to infer the subtask that the human is currently performing, allowing the helper to assist the human in performing the correct task. Experiments show that the method can be effective, giving near-human level performance in helping a human in a collaborative game.

We present ongoing work on a system that accommodates player agency in a digital narrative with an external plot. We focus on key events that should occur in that storyline for dramatic effect, but do not explicitly specify the characters that should fill the roles needed for those events. Instead, we define them abstractly, with characteristics that the selected characters should have (including previous events they should have completed for eligibility), and rely on a Director construct to populate those roles from agents in the selection pool that fit those criteria. Agents begin as largely homogeneous, primordial entities that accumulate data and narrative value from the events in which they participate. This creates an environment that differentiates characters by the actions they perform, conferring worth onto characters that become important to the player based on their direct involvement in the plot. The focus, then, is on defining a priori the what of the narrative, while leaving it to the Director construct to decide at runtime exactly who among a distributed pool of agents carries it out.

The creation of effective autonomous agents (bots) for combat scenarios has long been a goal of the gaming industry. However, a secondary consideration is whether the autonomous bots behave like human players; this is especially important for simulation/training applications which aim to instruct participants in real-world tasks. Bots often compensate for a lack of combat acumen with advantages such as accurate targeting, predefined navigational networks, and perfect world knowledge, which makes them challenging but often predictable opponents. In this paper, we examine the problem of teaching a bot to play like a human in first-person shooter game combat scenarios. Our bot learns attack, exploration and targeting policies from data collected from expert human player demonstrations in Unreal Tournament. We hypothesize that one key difference between human players and autonomous bots lies in the relative valuation of game states. To capture the internal model used by expert human players to evaluate the benefits of different actions, we use inverse reinforcement learning to learn rewards for different game states. We report the results of a human subjects' study evaluating the performance of bot policies learned from human demonstration against a set of standard bot policies. Our study reveals that human players found our bots to be significantly more human-like than the standard bots during play. Our technique represents a promising stepping-stone toward addressing challenges such as the Bot Turing Test (the CIG Bot 2K Competition).

Annotated corpora have stimulated great advances in the language sciences. The time is ripe to bring that same stimulation, and consequent benefits, to computational approaches to narrative. I describe an effort to construct a corpus of semantically annotated stories. I outline the structure of the corpus, a structure which colloquially can be described as a "handful of handfuls." One handful of the corpus has already been constructed, viz., 18k words of Russian folktales. There are two handfuls under construction: legal cases focused on the area of probable cause, and stories from Islamist Extremist Jihadists. Four more handfuls are being planned: folktales from Chinese, English, and a West Asian culture, and stories of international conventional and cyber conflicts. There are numerous additional handfuls under discussion. The main focus of the corpus so far has been on textual materials that are annotated for their surface semantics using conventional annotation tools and techniques; nonetheless, there are numerous novel dimensions along which the corpus might grow and become useful for different communities. In particular I propose for discussion the outlines of a few novel sources, annotation schemes, and collection methodologies that could potentially make the corpus of great use to the interactive narrative or narrative generation communities.

Playtesting is the primary process that allows a game designer to access game quality. Current playtesting methods are often intrusive to play, involves much manual labor, and might not even portray the player's true feedback. This paper aims to alleviate these shortcomings by presenting the position that state of the art artificial intelligence techniques can construct automated playtesting systems that supplement or even substitute this process to a certain extent. Several potential research directions are proposed in this theme. A work-in-progress report is also included to demonstrate the conceptual feasibility of the potentials of this research area.

We have developed a method for detecting real money traders (RMTers) to support the operators of massively multiplayer online role-playing games (MMORPGs). RMTers, who earn currency in the real world by selling properties in the virtual world, tend to form alliances and frequently exchange a huge volume of virtual currency within such a community. The proposed method exploits (1) the trading network, to identify the communities of characters, and (2) the volume of trades, to estimate the likelihood of communities and characters becoming engaged in real money trading. The results of an experiment using actual log data from a commercial MMORPG showed that using the trading network is more effective in detecting RMTers than conventional machine learning methods that assess individual character without referring to the trading network.