Goal recognition is the task of inferring users’ goals from sequences of observed actions. By enabling player-adaptive digital games to dynamically adjust their behavior in concert with players’ changing goals, goal recognition can inform adaptive decision making for a broad range of entertainment, training, and education applications. This paper presents a goal recognition framework based on Markov logic networks (MLN). The model’s parameters are directly learned from a corpus of actions that was collected through player interactions with a non-linear educational game. An empirical evaluation demonstrates that the MLN goal recognition framework accurately predicts players’ goals in a game environment with multiple solution paths.

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.

We study the problem of learning probabilistic models of high-level strategic behavior in the real-time strategy (RTS) game StarCraft. The models are automatically learned from sets of game logs and aim to capture the common strategic states and decision points that arise in those games. Unlike most work on behavior/strategy learning and prediction in RTS games, our data-centric approach is not biased by or limited to any set of preconceived strategic concepts. Further, since our behavior model is based on the well-developed and generic paradigm of hidden Markov models, it supports a variety of uses for the design of AI players and human assistants. For example, the learned models can be used to make probabilistic predictions of a player's future actions based on observations, to simulate possible future trajectories of a player, or to identify uncharacteristic or novel strategies in a game database. In addition, the learned qualitative structure of the model can be analyzed by humans in order to categorize common strategic elements. We demonstrate our approach by learning models from 331 expert-level games and provide both a qualitative and quantitative assessment of the learned model's utility.

We address the challenges of evaluating the fidelity of AI agents that are attempting to produce human-like behaviors in games. To create a believable and engaging game play experience, designers must ensure that their non-player characters (NPCs) behave in a human-like manner. Today, with the wide popularity of massively-multi-player online games, this goal may seem less important. However, if we can reliably produce human-like NPCs, this can open up an entirely new genre of game play. In this paper, we focus on emulating human behaviors in strategic game settings, and focus on a Social Ultimatum Game as the testbed for developing and evaluating a set of metrics for comparing various autonomous agents to human behavior collected from live experiments.

Current behavior authoring tools force game designers to split their attention between the game context and the tool context. We have addressed this problem by developing a behavior authoring tool that merges these two contexts. This paper outlines the design and implementation of a gameindependent behavior tree authoring tool, called AIPaint, that allows a designer to create and edit behavior trees via a natural sketching interface overlaid on the game world. We demonstrate the use of AIPaint to author computercontrolled characters in two simple games and report on an observational evaluation.

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 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.

Game metrics are an approach to understanding games and gameplay by analyzing and visualizing information collected from players in playtests. This paper proposes that another source of metrics is the game itself, and that not all information needs to (or ought to) come from empirical playtests. I discuss seven strategies for extracting information from games, and discuss how the information retrieved in this manner relates to empirical playtest metrics---which it differs from but can often complement.

Due to the changing nature of videogames, the component-based architecture is the design of choice for managing game entities instead of the traditional static class hierarchies. A component-based architecture lets programmers edit entities as collections of components, which provide the entity with new functionalities. Such architecture promotes flexibility but makes the code more difficult to understand because entities are built at runtime by linking components. In this paper we present a semi-automatic process for moving from a class hierarchy to a component-based architecture. Through the application of Formal Concept Analysis we propose a novel technique for automatically identifying candidate distributions of responsibilities among components.

This paper presents the latest version of the Machinations framework. This framework uses diagrams to represent the flow of tangible and abstract resources through a game. This flow represents the mechanics that make up a game’s interbal economy and has a large impact on the emergent gameplay of most simulation games, strategy games and board games. This paper shows how Machinations diagrams can be used simulate and balance games before they are built.