Group items tagged

From the abstract: "Collective Artificial Intelligence (CAI) simulates human intelligence from data contributed by many humans, mined for inter-related patterns. This thesis applies CAI to social role-playing, introducing an end-to-end process for compositing recorded performances from thousands of humans, and simulating open-ended interaction from this data. The CAI process combines crowdsourcing, pattern discovery, and case-based planning. Content creation is crowdsourced by recording role-players online. Browser-based tools allow non-experts to annotate data, organizing content into a hierarchical narrative structure. Patterns discovered from data power a novel system combining plan recognition with case-based planning. The combination of this process and structure produces a new medium, which exploits a massive corpus to realize characters who interact and converse with humans. This medium enables new experiences in videogames, and new classes of training simulations, therapeutic applications, and social robots. .... As a proof of concept, a CAI system has been evaluated by recording over 10,000 performances in The Restaurant Game, automating an AI-controlled waitress who interacts in the world, and converses with a human via text or speech. Quantitative results demonstrate CAI supports significantly open-ended interaction with humans, while focus groups reveal factors for improving engagement."

Abstract: "Game Artificial Intelligence (Game AI) is a subdiscipline of Artificial Intelligence (AI) and Machine Learning (ML) that explores the ways in which AI and ML can augment player experiences in computer games. Storytelling is an integral part of many modern computer games; within games stories create context, motivate the player, and move the action forward. Interactive Narrative is the use of AI to create and manage stories within games, creating the perception that the player is a character in a dynamically unfolding and responsive story. This paper introduces Game AI and focuses on the open research problems of Interactive Narrative."

"The UT^2 game bot, created by computer scientists Jacob Schru, Igor Karpov and Risto Miikkulainen, won the Humanlike Bot Competition at the IEEE World Congress on Computational Intelligence (WCCI 2012). "The idea of the competition is to evaluate how we can make game bots, non-player characters (NPCs) controlled by AI algorithms, appear as human as possible," explains Miikkulainen, professor of computer science in the College of Natural Sciences. "It is generally recognized that NPCs are relatively weak in most video games: their behavior is predictable and mechanical, and they often make mistakes that human players would be unlikely to make. Players often enjoy playing against other humans, because it provides a more interesting game experience. The goal of the competition is to promote more research in human-like bots, as well as evaluate how well we are currently doing in this area."

Abstract: "In recent years, there has been a dramatic proliferation of research concerned with game based learning and intelligent system s . Although the intelligent agent bas ed system has existed for many years, only recently its surge of mainstream popularity motivated researchers to acknowledge its educational value. With the increasing usage of game based learning, reliability requirements for intelligent system s or multi - a gent system s have become more critical. Quiz game is one of the game types which is easy to develop and not restrict ed by any specific subject and any people . And the m ulti - agent based system is flexible and saving resource . Hence we integrate the quiz gam e into multi - agent system s , we called it m ulti - agent based quiz game and also d evelop a framework to build personalized assessment game . For the instructor, they can understand student's playing situation and experience . For the students, they have p ersona lized assessment game . In this paper, we proposed a framewor k of multi - agent based Quiz - MASter , and describe each service from each agent briefly."

Her name is Angelina: she runs on a heavy-duty Mac server and she's building some addictive computer games for you. Angelina (a tail-recursive acronym for "A Novel Game-Evolving Labrat I've Named ANGELINA") is a project in evolutionary computing by Michael Cook, a PhD candidate at Imperial College in the UK.

Abstract: "Non-player Characters (NPCs) that accompany the player en- able a single player to participate in team-based experiences, improving immersion and allowing for more complex game- play. In this context, an Artificial Intelligence (AI) teammate should make good combat decisions, supporting the player and optimizing combat resolution. Here we investigate the target selection problem, which consists of picking the op- timal enemy as a target in a modern war game. We look at how the companion's different strategies can influence the outcome of combat, and by analyzing a variety of non-trivial First Person Shooter (FPS) scenarios show that a mathemat- ically simple approach significantly improves over common strategies typically found in games, and can achieve results similar to much more expensive look-up tree approaches. This work has applications in practical game design, show- ing that simple, computationally efficient target selection can make an excellent target selection heuristic"

Abstract: "Abstract Game developers spend a large portion of their time developing and tweaking the articial intelligence in video games. Problems related to productivity in the development of AI have been solved using various modeling techniques in the eld of AI, language design and easier to use editors. Using a domain specic language to assist in describing AI can increase productivity in this area. In addition to this, game developers can be relieved from irrelevant tasks such as worrying about performance, correctness of the implementation, memory management and optimiza- tion data structures and focus on the high level description of the game play. In this thesis, we focus on real-time video games and we investigate the development of a domain-specic language containing the necessary elements to describe and execute strategies to achieve goals in a real-time video game. We develop a domain-specic language to express strategies for computer controlled actors using techniques commonly found in em- bedded domain-specic languages, and in particular embedded domain- specic languages in Haskell. To demonstrate this language we have developed a prototype of a real-time strategy game that uses strategies implemented using the domain-specic language developed in this thesis"

Abstract: "A number of changes are occurring in the field of computer game development: persistent online games, digital distribution platforms, social and mobile games, and the emer- gence of new business models have pushed game development to put heavier emphasis on the live operation of games. Artificial intelligence has long been an important part of game development practices. The forces of change in the industry present an opportunity for Game AI to have new and profound impact on game development practices. Specifically, Game AI agents should act as "producers" responsible for managing a long-running set of live games, their player communities, and real-world context. We characterize a confluence of four major forces at play in the games industry today, together producing a wealth of data that opens unique research opportunities and challenges for Game AI as producers. We enumerate 12 new research areas spawned by these forces and steps toward how they can be addressed by data-driven Game AI Producers"

Abstract: "We propose a powerful new tool for conducting research on computational intelligence and games. 'PyVGDL' is a simple, high-level description language for 2D video games, and the accompanying software library permits parsing and instantly playing those games. The streamlined design of the language is based on defining locations and dynamics for simple building blocks, and the interaction effects when such objects collide, all of which are provided in a rich ontology. It can be used to quickly design games, without needing to deal with control structures, and the concise language is also accessible to generative approaches. We show how the dynamics of many classical games can be generated from a few lines of PyVGDL."

Abstract: "A recent trend within computational intelligence and games research is to investigate how to affect video game players' in-game experience by designing and/or modifying aspects of game content. Analysing the relationship between game content, player behaviour and self-reported affective states constitutes an important step towards understanding game experience and constructing effective game adaptation mechanisms. This papers reports on further refinement of a method to understand this relationship by analysing data collected from players, building models that predict player experience and analysing what features of game and player data predict player affect best. We analyse data from players playing 780 pairs of short game sessions of the platform game Super Mario Bros, investigate the impact of the session size and what part of the level that has the major affect on player experience. Several types of features are explored, including item frequencies and patterns extracted through frequent sequence mining."

"Driven by an initiative of the Adult & Paediatric Diabetes Psychology Service of New Zealand, research has been performed to develop new mechanisms, in the form of computer games, to educate children and teenagers about living with diabetes. Aimed at achieving maximum education effectiveness, the ultimate goal of our research is to develop innovative machine learning algorithms that can be used in games to improve their ability to learn about the changing needs of children and to incorporate this intelligence into the game interface. We also plan to collect and report on the information collected from testing our computer games within a small group of children who have been diagnosed with type I diabetics. "

"We argue that the development of innovative artificial intelligence (AI) systems plays a crucial role in the exploration of currently unreachable spaces. To aid in exploration, we suggest a practice called AI-based game design, an iterative design process that deeply integrates the affordances of an AI system within the context of game design."

"Abstract-While component reuse is a common concept in software engineering, it does not yet have a strong foothold in Computer Game development, in particular the development of computer-controlled game characters. In this work, we take a modular Statechart-based game AI modelling approach and develop a reuse strategy to enable fast development of new AIs. This is aided through the creation of a standardized interface for Statechart modules in a layered architecture. Reuse is enabled at a high-level through functional groups that encapsulate behaviour. These concepts are solidified with the development of the SkyAI tool. SkyAI enables a developer to build and work with a library of modular components to develop new AIs by composing modules, and then output the resulting product to an existing game. Efficacy is demonstrated by reusing AI components from a tank to quickly make a much different AI for a simple animal."

"As research for a Ph.D. thesis, we propose to show that a layered Statechart-based AI is a suitable formalism for Game AI, enabling the use of model-driven development techniques such as reuse and high-level analysis including model-checking. The fundamentally modular nature of this approach leads naturally to reuse as a fundamental component of the design process. Supported by a clearly defined formalism, useful behavioural analyses become possible, such as testing reactions to various inputs at design time. We also explore transformations at the modelling level to enable procedural generation, allowing rapid deployment of varying AIs. Additionally, such a model allows for the generation of efficient code that can be directly inserted into games. Tool support for reuse, generation, and analysis will be developed, then employed in creating an industrial scale AI, proving that this formalism is appropriate for industrial use."

Abstract: "Intelligent Tutoring Systems (ITSs) have begun to develop hybrid systems that balance the learning benefits of ITSs with the motivational benefits of games. iSTART-ME (Motivationally Enhanced) is a new game-based learning environment developed on top of an existing ITS for reading comprehension (iSTART). In an 11 session labbased study, 40 high school students interacted with the full iSTART-ME system and completed comprehension measures at multiple time points (pretest, posttest, retention, and transfer). The current work examined students' comprehension outcomes and how they were related to performance within three integrated practice methods: Coached Practice (non-game), Showdown (game-based), and Map Conquest (game-based). Results indicate that performance within the game-based practice environments was positively related to comprehension outcomes, whereas performance within the non-game environment had no relation to subsequent comprehension measures."

From the abstract: " this paper, we challenge the assumption that feedback during learning hinders sense of presence. Ac ross three experiments, we examined how an ITS that provided extrinsic feedback during a serious game affected presence. Across different modalities and conditions, we found that feedback and other ITS features do not always affect presence. Our results suggest that it is possible to provide extrinsic feedback in a serious game without detracting from the immersive power of the game itself. "

Abstract: "This paper explores the use of modern sensor technologies for physical interaction on educati onal games and interactive spaces. More specifically the thesis studies the potential effect of motion capture and wearable body sensors on educational interactive games, on two aspects: i) on the involvement of human body and motion in the process of lear ning, and recall of knowledge (embodied learning), ii) on assisting the development of basic social emotional competencies, through the enhanced social affordances of embodied games. The paper presents a prototype of an educational game developed using a m otion capture controller and two bio feedback sensors, proposing a generic architecture for multi sensor interactive spaces. Finally the paper provides a review of previously studied modalities for emotion recognition, and examines their application on gam e mechanics and AI game agents."

From the abstract: "Here we demonstrate for the first time the iterative development of agent behaviour for a real-time strategy game (here StarCraft) utilising Behaviour Oriented Design (BOD) [7]. BOD provides focus on the robust creation and easy adjustment of modular and hierarchical cognitive agents. We demonstrate BOD's usage in creating an AI capable of playing the StarCraft character the Zerg hive mind, and document its performance against a variety of opponent AI systems. In describing our tool-driven development process, we also describe the new Abode IDE, provide a brief literature review situating BOD in the AI game literature, and propose possible future work."

"Two-Population Novelty Search for Generating Game Content"

Proposal to allow "experiment with AI bots," considering gaming competitions and Blizzard online games