Conversational Agents in a Virtual World

Affective game engines could support game development by providing specialized emotion sensing (detection), emotion modeling, emotion expression and affective behavior generation explicitly tailored towards games. In this chapter we discuss the rationale for specialized emotional appraisal engines for games, analogous to having specialized physics engines. Such engines provide basic emotion modeling capabilities to generate emotions for Non Player Characters (NPCs), just like the Havok engine provides physics-related special purpose processing. In particular, such engines provide NPCs with an emotional state by simulating the emotional meaning of an event to an NPC in the context of the game’s storyline, the NPC’s personality, and relationships with other NPCs. We discuss why such engines are needed, present an example approach based on cognitive appraisal, and show how this appraisal engine has been integrated in a wide variety of architectures for controlling NPCs. We conclude with a discussion of novel gameplays possible by the more sophisticated emotion modeling enabled by an emotion appraisal engine.

For the last few decades, there was tremendous interest in harnessing 3D virtual environments for education and training. Multi-user game-like environments make use of non-player characters and quest activities in tutoring and training. This approach incorporates successful active learning and incremental progress. This article presents issues encountered while adapting the multi-user online game genre for educational virtual environments. In this endeavour, non-player characters play a central role in organising and delivering educational content. Educational virtual environments call for additional kinds of extension beyond generic user content creation as delivered in some virtual worlds like Second Life. Support for these environments will emphasise the creation of new activities. A set of libraries and techniques named portable non-player character tutors and quests reduces the effort needed to develop and integrate educational non-player characters. These non-player characters are introduced in CVE, a platform for rapidly developing educational virtual environments. The portable non-player character tutors and quests framework enables formatted web-based exercises, quizzes, and educational content to be incorporated into virtual worlds, reducing the effort needed to create new content. The framework presented in this article introduces initial non-player characters that support educational quest activities to the 3D environments users.

Non-playable Character (NPC) is one of the important characters in the game. An autonomous and adaptive NPC can adjust actions with player actions and environmental conditions. To determine the actions of the NPC, the previous researchers used the Neural Network method but there were weaknesses, namely the action produced was not in accordance with the desired so the accuracy was not good. This study overcomes the problem of poor accuracy by using the Logarithmic Learning for Generalized Classifier Neural Network (L-GCNN) method with 6 input parameters, NPC health, distance from players, other NPCs involved, attack power, number of NPCs and NPC levels. While the output is to attack itself, attack in groups and move away. For testing, this study was tested on RPG games. From the results of the experiments conducted, it shows that the L-GCNN method has better accuracy than the 3 methods compared to 7% better than NN and SVM and 8% better than RBFNN because in the L-GCNN method there is an encapsulation process that is data have the same class will. Whereas the L-GCNN training time is 30% longer than the NN method because on L-GCNN one neuron consists of one data where there are fewer NNs in the hidden layer.

This paper firstly seeks an answer to the question of whether Non Player Characters (NPCs) in Computer Games can also be viewed as game agents where reactivity, autonomy, being temporarily continuous and having goal-oriented behavior are taken as the features of being a game agent. Within this scope, we will try to assess whether naming NPCs as agents point to a desire that one day they would fulfill the requirements of being an agent or whether NPCs actually already fulfill these requirements. Secondly, the paper looks into the AI needs of video games. We present the AI methodologies that are either being used and under research for use in Game AI. The same methodologies are also likely to contribute to the increasing levels of autonomy and goal-directed behavior of NPCs and help them become more agent-like.

Most of the existing Virtual World (VW)-based curriculum-related educational systems use conventional non-player characters (NPCs) to interact with users, represented as avatars, to guide and help them to accomplish learning activities. Also, a few of them use some kind of gamification and keep data for user interactions and activities, and even fewer allow for real-time tutor intervention. In this paper, we present the design, implementation, and evaluation of an educational system based on VW technology, which employs gamification features; two types of NPCs, one conventional and another LLM-based; and a database that stores, apart from educational information, information about the interactions users have with NPCs. Furthermore, we designed and implemented a learning management unit for online-tutor tracing and for supporting the learning progress of users. The evaluation of the system, via experimental use and questionnaires, shows that both types of NPCs were useful for different reasons, although there was a preference for the LLM-based NPC. LLM-based NPCs made dialogues more interesting and were perceived as more friendly and helpful, but conventional ones provided more targeted help. However, both were less interesting than the two gamification features: a scoring system and quizzes. Additionally, the effectiveness of the tutoring system was confirmed in terms of learning outcomes and overall experience, although in a subjective manner. Finally, online-tutor support was recognized as a very positive capability.

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.

Game is a form of interactivity where player and game world interact to each other. In a game, one of the elements which can be considered necessary to support the course and the reality of the game is how a NPC (Non-Player Character) in the game moves. A* (A-star) is an algorithm which can be used to perform pathfinding. In this case, A* will be used to find a shortest distance between the NPC and the player character. This research was performed to conduct experiments on the implementation of the A* algorithm in the 3D game. The research will be conducted by implementing an A* algorithm to a game, precisely to the enemy characters that exist in the game. Once the implementation was conducted, an experiment will performed using certain cases as a proving ground for the implementation. As a conclusion, from a hundred experiments, A* algorithm always can find the path for enemy to catch player and 73% of them are optimal paths.

As artificial intelligence becomes increasingly integrated into virtual environments—shaping avatars, non-player characters (NPCs), and decision-making systems—the ethical landscape of digital worlds is being profoundly reshaped. This paper explores the ethical implications of AI-driven agents within virtual spaces, focusing on issues of autonomy, accountability, and moral influence. By examining how intelligent avatars and NPCs can reinforce or challenge user behaviors, perpetuate biases, or simulate moral reasoning, we argue that developers and stakeholders must adopt ethical frameworks for the design and governance of virtual AI. We analyze case studies from gaming, metaverse platforms, and educational simulations to highlight ethical tensions arising from deception, emotional manipulation, surveillance, and consent. Finally, we propose guidelines for responsible AI implementation in virtual worlds that respect user dignity, promote fairness, and encourage transparent interaction between human and synthetic agents.

The paper presents an emergency situation simulation game developed at the home institution of the authors as a system of emotional agents on the Jadex platform enhanced by the JBdiEmo emotional engine, which implements the OCC emotional model. It demonstrates usability of Jadex and JBdiEmo for development of such games, explains how the player and non-playable characters are represented by emotional BDI agents, explores limits of 3D visualization support of Jadex and provides some solutions on how to overcome them.

Popular games often have a high-quality graphic design but quite simple-minded non player characters (NPC). Recently, Computational Intelligence (CI) methods have been discovered as suitable methods to revive NPC, making games more interesting, challenging, and funny. We present a fairly large study of human players on the simple arcade game Pac-Man, controlling the ghosts behaviors by simple strategies, neural networks or evolutionary algorithms. The playerpsilas fun is of course a subjective experience, but we presume that it is related to the psychological flow concept. We deal with the question whether flow is a more reliable measure than asking human players directly for the fun experienced during the game. In order to detect flow, we introduce a measure based on the interaction time fraction between the human-controlled Pac-Man and the ghosts, and compare the outcome to the results of a fun measure suggested by Yannakakis and Hallam [1].

Video games are a means of entertainment for everyone, from children to adults. The genre of games now is also very diverse, ranging from adventure, puzzles to storytelling, and even many folk stories have been made into video games by several developers in Indonesia. Starting from folk tales with horror themes such as kuntilanak, legends such as cucumber mas, to folk tales that rarely sound like golden oranges. The folklore video game of buah jeruk emas is a video game that tells of a king who gets a whisper from the gods to get golden oranges. The king then held a competition to get the golden orange fruit. The player must be able to take the golden orange fruit from the enemy in the form of a Non Playable Character (NPC) who will chase the player. In making NPCs, algorithms are used to help play video games. Therefore, the author wants to apply the A * algorithm in the game of golden oranges so that npc can catch up to players according to the planned system. The main method used is A * and then the addition of the FSM method for other methods. The golden orange fruit is a video game using the A * algorithm and the FSM method after testing it can be concluded that it is enough to make the game run. With the results according to the planned system.

A novel approach to a decentralized autonomous model of agency for general purpose Non-Player Characters (NPCs) is presented: Computational Ecosystems as a model of AI. We describe the technology used to animate a population of gregarious humanoid characters in the virtual world Where is Lourenco Marques? an ethnographic artistic work characterized as a virtual world inhabited by a population of NPCs interacting autonomously among themselves as well as with an audience of outsiders (human observers). First, we present the background and motivations for the project. Then, we describe the technical details about the algorithm that was developed to generate the movements and behaviors of a population of NPC ‘storytellers’. Finally, we layout some of the critical aspects of this particular implementation and contextualize the work with regards to a wider usage in virtual worlds.

Role-playing video games can highlight a sense of player identification with a pre-made player-character through the inclusion of the voice; this can include diegetic character dialogue, the non-diegetic sung voice, and voice-overs. Ensuring that the player can connect with their player-character on an individual level is key to forming a suspension of disbelief and immersion with a game. Final Fantasy XV emphasizes collaboration between the player, player-characters, and non-playable characters during combat, cutscenes, and exploration. This camaraderie effect actively engages the player with multiple characters through the constant use of the diegetic spoken voice to communicate between the player-character, Noctis, and the three other character identities, Prompto, Ignis, and Gladiolus. The game’s opening rendition of Ben E. King’s “Stand by Me,” performed by Florence + the Machine, provides the player with four narrative themes that are present throughout the game. These themes include a coming-of-age story, character relationships, and the development of a greater evil within the narrative. Unique in its position as a pre-composed song, “Stand by Me” plants the idea that the player will not be alone in their journey, as character allies will stand by Noctis, from the beginning of the game. Final Fantasy XV uses vocalizations in both the diegetic and non-diegetic audio space in order to reflect the characteristics of the playable characters. The vocal relationship between the player’s characters provides directional feedback and information for the player within combat, alongside foretelling the stories of certain characters.

Abstract: Applications of fuzzy logic in game creation have proven useful, especially when it comes to modelling the behavior of non-player characters (NPCs) in video games. NPC behavior in video games has historically been governed by strict rule-based systems or scripted sequences, which frequently led to restricted and predictable interactions. On the other hand, fuzzy logic adds a degree of flexibility and ambiguity to the decision-making processes of NPCs. By improving the naturalness, adaptability, and emotional resonance of NPC behavior, fuzzy logic may greatly enhance player experiences in games. It provides players with progressively more engaging and dynamic gaming experiences as it continues to be incorporated into game production, opening up new possibilities for interactive narrative, gaming, and immersive virtual worlds. Based on Utku Kose's article, "Developing a Fuzzy Logic Based Game System," I have investigated the use of fuzzy logic in gaming contexts for NPC decision-making in this study.

CHI Systems, under contract to the U. S. Army Research Institute, developed an immersive training system, called Virtual Environment Composable Training for Operational Readiness Training Delivery (VECTOR-TD), which provides scenario-based virtual environments for cultural familiarization. VECTOR-TD was designed to provide a new technology for game-based training in cultural familiarization through the application of scenario-based training. VECTOR-TD integrates the Lithtech Jupiter game engine for the virtual environment and CHI System’s iGEN® cognitive agent development toolkit to implement intelligent game characters and integrated performance monitoring. In order for VECTOR-TD to have true long term value to the Army, it was determined that it would be necessary to develop content management tools which would allow Army training personnel to edit and author VECTOR-TD scenarios. To address this, VECTOR-Scenario Editor (VECTOR-SE) was developed based on VECTOR-TD XML-based scripting language to externalize the representation of the training scenario, the behavior of non-player characters (NPCs) within the scenario, and the behavior of the instructor NPC responsible for performance evaluation and After Action Review (AAR). The XML-based language provides direct control of the behavior, dialog, emotional state, and predispositions of NPCs within the scenario. VECTOR-SE was successfully developed to provide content development and management tools that allow non-programmers to author scenarios and manipulate training parameters. VECTOR-SE is based on an instructional design process model and involves the specification of learning objectives, the creation of scenario segments (i.e., vignettes), the authoring of character/trainee dialog, the designation of dialog branching, the placement of characters at game locations, and the designation of when training assistance/remediation will be delivered. The significance of VECTOR-SE is twofold. First, it drastically reduces the time and skill required to develop VECTOR scenarios. Within the original VECTOR project, a 15-minute cultural training scenario was developed which required 2 months of programming and cognitive modeling effort. The same scenario was later implemented in VECTOR-SE in under 3 days. Additional scenarios with comparable complexity have also been implemented using VECTOR-SE and similar significant reductions in development time have been observed. 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.