New entry in Digiplay games research bibliography:

New entry in Digiplay games research bibliography:

Leveraging the prevailing interest in computer games among college students, both for entertainment and as a possible career path, is a major reason for the increasing prevalence of computer game design courses in computer science curricula. Because implementing a computer game requires strong programming skills, game design courses are most often restricted to more advanced computer science students, yet real game design involves a diverse and creative team. This paper reports on a ready-made game design and experimentation framework, implemented in Java, which makes game programming more widely accessible. This framework, called Labyrinth, enables students at all programming skill levels to participate in computer game design. We describe the architecture of the framework, and discuss programming projects suitable for a wide variety of computer science courses, from capstone to non-major.

New entry in Digiplay games research bibliography:

Computer games have been around for almost as long as computers. Most of these games, however, have been designed in a rather ad hoc manner because many of their basic components have never been adequately defined. In this paper some deficiencies in the standard model of computer games, the minimax model, are pointed out and the issues that a general theory must address are outlined. Most of the discussion is done in the context of control strategies, or sets of criteria for move selection. A survey of control strategies brings together results from two fields: implementations of real games and theoretical predictions derived on simplified game-trees. The interplay between these results suggests a series of open problems that have arisen during the course of both analytic experimentation and practical experience as the basis for a formal theory.

New entry in Digiplay games research bibliography:

This paper overviews some of the main components of the AI system for The Suffering, a single-player 1st/3rd-person action/horror game by Surreal Software for the PlayStation 2 (PS2) and XBox consoles (2004). A simpler version was used in the PC and PlayStation 2 versions of Lord of the Rings: The Fellowship of the Ring (2002). The behavior hierarchy, pathfinding, and steering components are described. The AI system was designed to satisfy goals based on lessons learned from previous projects and work within the constraints of developing a commercial title for videogame consoles. The main goals were to have: a modular behavior system able to support a large variety of behaviors, memory-efficient and robust saved games, many distinct NPC types with different styles of movement and combat, fast and robust pathfinding, robust movement and collision, and modular steering behaviors. The goals were largely met, though some issues became apparent in the course of development, primarily difficulties for designers with setting up movement graphs and NPC logic.

New entry in Digiplay games research bibliography:

Purpose - The main intention of this paper is to state the benefits of using online videogames as a research environment, where AI algorithms are improved by means of learning from real-human-behaviour examples. Design/methodology/approach - The manner of taking advantage from the flux of real-human-behaviour examples inside an online videogame is stated. Then Mad University, a prototype online videogame specifically conceived and developed for this purpose, is explained. Findings - Human-like AI in artificial algorithms can be boosted by means of a specific kind of online videogame called MMORPGs, used as a research environment. Research limitations/implications - Mad University is a prototype videogame which has been developed to experiment with AI algorithms that aim to learn strategies in a generalized fashion. The next research step will be to improve Mad University and to put it to work with hundreds of players and then research and test the effectiveness of the AI algorithms. Originality/value - This paper proposes a new way of testing and experimenting with AI algorithms in order to obtain more human-like results, and claims to have attempted to develop a generalized learning method.

New entry in Digiplay games research bibliography:

Game artificial intelligence (AI) controls the decision-making process of computer-controlled opponents in computer games. Adaptive game AI (i.e., game AI that can automatically adapt the behaviour of the computer players to changes in the environment) can increase the entertainment value of computer games. Successful adaptive game AI is invariably based on the game's domain knowledge. We show that an offline evolutionary algorithm can learn important domain knowledge in the form of game tactics (i.e., a sequence of game actions) for dynamic scripting, an offline algorithm inspired by reinforcement learning approaches that we use to create adaptive game AI. We compare the performance of dynamic scripting under three conditions for defeating non-adaptive opponents in a real-time strategy game. In the first condition, we manually encode its tactics. In the second condition, we manually translate the tactics learned by the evolutionary algorithm, and use them for dynamic scripting. In the third condition, this translation is automated. We found that dynamic scripting performs best under the third condition, and both of the latter conditions outperform manual tactic encoding. We discuss the implications of these results, and the performance of dynamic scripting for adaptive game AI from the perspective of machine learning research and commercial game development.

New entry in Digiplay games research bibliography:

This paper presents an imitation learning system capable of learning tasks in a complex dynamic real-time environment. In this paper, we argue that social learning should be thought of as a special case of general skill learning, and that the biases it presents to the skill learning problem radically simplify learning for species with sufficient innate predisposition to harness this power. We decompose skill learning into four subproblems, then show how a modification of Roy's CELL system can address all these problems simultaneously. Our system is demonstrated working in the domain of a real-time virtual-reality game, Unreal Tournament.

New entry in Digiplay games research bibliography:

This paper describes the design and implementation of a module of emotions and personality for synthetic actors. Here are presented the results of previous researches, which were the basis of this project. With this information, a model for emotion generation using personality traits was designed in three stages, and implemented. using fuzzy logic, FSMs, and probability theory. Finally, the functionalities of the module were shown using a demo version implemented with the videogame engine Unreal (R) 2 Runtime.

New entry in Digiplay games research bibliography:

Game studies has yet to engage with a sustained debate on the implications of its fundamentally technologically based foundation – i.e. the ‘digitality’ of digital games. This paper calls for such a debate and offers some initial thoughts on issues and directions. The humanities and social sciences are founded on the principle that historical and cultural agency reside solely in the human and the social. Drawing on Science and Technology Studies, Actor-Network Theory and cybercultural studies, this paper argues that a full understanding of both the playing of digital games, and the wider techno-cultural context of this play, is only possible through a recognition and theorisation of technological agency. Taking the Gameboy Advance game Advance Wars 2 as a case study, the paper explores the implications for game studies of attention to non-human agency – specifically the agency of simulation and artificial life software - in digital game play.