A growing issue in the development of realistic and entertain-ing interactive games is the need for mechanisms that support ongoing natural language conversation between human players and artificial non-player characters. Unfortunately, many methods for implementing natural language generation(NLG) induce a significant burden on the author, do not scale well, or require specialized linguistic knowledge. We formalize the notion of typed-templates, an extension of standard structures employed in template-based NLG. We further provide novel algorithms that, when applied to typed-templates, ameliorate the above issues by affording computational support for authoring and increased variation in utterance and scenario generation. We demonstrate the efficacy of typed-templates and the algorithms through a user study.

This paper presents a search-based approach to generating game content that satisfies both gameplay requirements and user-expressed aesthetic criteria. Using evolutionary constraint satisfaction, we search for spaceships (for a space combat game) represented as compositional pattern-producing networks. While the gameplay requirements are satisfied by ad-hoc defined constraints, the aesthetic evaluation function can also be informed by human aesthetic judgement. This is achieved using indirect interactive evolution, where an evaluation function re-weights an array of aesthetic criteria based on the choices of a human player. Early results show that we can create aesthetically diverse and interesting spaceships while retaining in-game functionality.

Hiding and seeking is a cognitive ability frequently demonstrated by humans in both real life and video games. We use machine learning to automatically construct the first computational model of hide/seek behavior in adult humans in a video game like setting. The model is then run generatively in a novel environment and its behavior is found indistinguishable from actual human behavior by a panel of human judges.  In doing so the artificial intelligence agent using the model appears to have passed a version of the Turing test for hiding and seeking.

A big challenge for creating human-level game AI is building agents capable of operating in imperfect information environments. In real-time strategy games the technological progress of an opponent and locations of enemy units are partially observable. To overcome this limitation, we explore a particle-based approach for estimating the location of enemy units that have been encountered. We represent state estimation as an optimization problem, and automatically learn parameters for the particle model by mining a corpus of expert StarCraft replays. The particle model tracks opponent units and provides conditions for activating tactical behaviors in our StarCraft bot. Our results show that incorporating a learned particle model improves the performance of EISBot by 10% over baseline approaches.

Conflict is an essential element of interesting stories, but little research in computer narrative has addressed it directly. We present a model of narrative conflict inspired by narratology research and based on Partial Order Causal Link (POCL) planning. This model informs an algorithm called CPOCL which extends previous research in story generation. Rather than eliminate all threatened causal links, CPOCL marks certain steps in a plan as non-executed in order to preserve the conflicting subplans of all characters without damaging the causal soundness of the overall story.

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).

This paper describes the creation of a digital improvisational theatre game, called Party Quirks, that allows a human user to improvise a scene with synthetic actors according to the rules of the real-world Party Quirks improv game. The AI actor behaviors are based on our study of communication strategies between real-life actors on stage and the fuzzy concepts that they employ to define and portray characters. This paper describes the underlying fuzzy concepts used to enable reasoning in ambiguous environments, like improv theatre. It also details the development of content for the system, which involved the creation of a system for animation authoring, design for efficient data reuse, and a work flow centered on Google Docs enabling parallel data entry and rapid iteration.

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 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.

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.