Behavior Of Non-player Characters Research Articles

Définir des individualités pour des personnages non joueurs

Designing the behaviour of non player characters (NPC), in role-playing video games, is a hard problem both from the programming point of view and from behaviour modelling considerations. We tackle these hurdles with the interaction oriented approach, promoted by the IODA-CoCoA project. It enables us to propose a generic engine suitable to several contexts. This engine is combined with an action selection mechanism based on motivations. This mechanism provides means to define several NPC behaviours by tuning the motivation parameters without new programming code. Our proposition constitutes a behavioural engine dedicated to the modelling of situated character behaviour. Thanks to its genericity, this engine can be used in various environment (ie games) and for various agents, since it adapts to individual specificities and abilities while proposing a diversity in designed behaviours.

Modeling motivation for adaptive nonplayer characters in dynamic computer game worlds

Current computer games are being set in increasingly more complex and dynamic virtual environments. Massively multiplayer online games, for example, are played in persistent virtual worlds, which evolve and change as players create and personalize their own virtual property. In contrast, technologies for controlling the behavior of nonplayer characters that populate virtual game worlds are frequently limited to preprogrammed rules. Characters using fixed rule-sets lack the ability to adapt in time with their environment. Motivated reinforcement learning offers an alternative to character design that can achieve nonplayer characters that both evolve and adapt in dynamic environments. This article presents and evaluates two computational models of motivation for use in nonplayer characters in persistent computer game worlds. These models represent motivation as an ongoing search for novelty, interest, and competence. Two metrics are introduced to evaluate the adaptability of characters controlled by motivated reinforcement learning agents using different models of motivation. These metrics characterize the behavior of nonplayer characters in terms of the variety and complexity of learned behaviors. An empirical evaluation of characters in simulated game scenarios shows that characters motivated by the search for competence are more adaptable in dynamic environments than those motivated by interest and novelty alone.

Guest Editors' Introduction: Intelligent Systems for Interactive Entertainment

This special issue presents research in innovative aspects of intelligent interactive entertainment (IE) that haven't seen much publication yet. AI researchers find IE interesting because it requires systems that think, behave, and interact the way that real people do. An invited article discusses the challenges, important trends, and future directions for intelligent IE. The other selected articles deal with a variety of topics: generating nonrepetitive behavior of nonplayer characters in video games; 3D virtual characters using speech, posture, pointing, and involuntary movements to interact with 2D presentations; applying a movie set metaphor to manage multiple software agents in dynamic scenarios; using spatial and temporal coherence as constraints for defining synchronization of actions and turn-taking in location-based games; adding humorous one-liners to text-based applications; and a user interface in which objects react and adapt to the user's focus of attention. This article is part of a special issue on interactive entertainment.

Generating Ambient Behaviors in Computer Role-Playing Games

Many computer games use custom scripts to control the ambient behaviors of nonplayer characters. As a result, story authors must write computer code for the game world's hundreds or thousands of NPCs. Creating entertaining, nonrepetitive NPC behaviors without investing substantial programming effort to write customized, nontrivial scripts is challenging. Current computer games have simplistic ambient behaviors for NPCs; it's rare for such characters to interact with each other. To address this, we developed a model that uses generative behavior patterns, which let authors quickly and reliably generate realistic and entertaining NPC scripts. The approach has proven successful, even in the challenging area of creating interactions between NPCs. This article is part of a special issue on interactive entertainment.

Virtual environment cultural training for operational readiness (VECTOR)

Abstract : An immersive training system, called Virtual Environment Cultural Training for Operational Readiness Training Delivery (VECTOR-TD), was developed to provide scenario-based virtual environments to support cultural familiarization. This paper describes the cultural-training application, the architectural design, and the associated implementation of the immersive environment and intelligent agent technology to control game non-player characters (NPC). One of the innovative features of the virtual environment is the use of executable cognitive models and emotion models which play significant roles in the overall reactions and behaviors of NPCs toward the trainee. In addition to influencing the behavior of the active NPCs, the emotion models constrain interactions with NPCs encountered later in a scenario. Recent additions to the VECTOR system include a scenario authoring capability that utilizes a graphical programming paradigm to enable scenario content authoring for execution within the VECTOR training system. The significance of VECTOR-SE is twofold. First, it dramatically reduces the time and skill required to develop VECTOR scenarios. Second, VECTOR-SE makes scenario development or modification accessible to a wider audience of professionals. VECTOR-TD and SE are currently being evaluated at the U.S. Military Academy at West Point.