game AI Research Papers - Academia.edu (original) (raw)

Computer games are an increasingly popular application for Artificial Intelligence (AI) research, and conversely AI is an increasingly popular selling point for commercial games. Although games are typically associated with entertainment, there are many "serious" applications of gaming, including military, corporate, and advertising applications. There are also so-called "humane" gaming applications for medical training, educational games, and games that reflect social consciousness or advocate for a cause. Game AI is the effort of going beyond scripted interactions, however complex, into the arena of truly interactive systems that are responsive, adaptive, and intelligent. Such systems learn about the player(s) during game play, adapt their own behaviors beyond the pre-programmed set provided by the game author, and interactively develop and provide a richer experience to the player(s). The long-term goal of our research is to develop artificial intelligence techniques that can have a significant impact in the game industry. In this paper, we present a list of challenges and research opportunities in developing techniques that can be used by computer game developers. We discuss three Case-Based Reasoning (CBR) (Aamodt & Plaza 1994), (Kolodner 1993) approaches to achieve adaptability in games: automatic behavior adaptation for believable characters; drama management and user modeling for interactive stories; and strategic behavior planning for real-time strategy games.

- by
- •
- Artificial Intelligent, Medical Training, game AI, Interactive Monitoring System

In this paper we try to determine the effectiveness of different AI techniques used in simple games. This effectiveness is measured by comparing game-play experience to implementation effort. Game-play experience is measured by letting a test panel play with the different kinds of AI techniques after which a questionnaire is filled in and the implementation effort is simply logged. The results showed that the increasing numbers of AI features is valued, but only until a certain level.

- by Arno Kamphuis
- •
- game AI

In this paper we try to determine the effectiveness of differ-ent AI techniques used in simple games. This effectiveness is measured by comparing game-play experience to implemen-tation effort. Game-play experience is measured by letting a test panel play with the different kinds of AI techniques af-ter which a questionnaire is filled in and the implementation effort is simply logged. The results showed that the increas-ing numbers of AI features is valued, but only until a certain level.

- by Arno Kamphuis
- •
- game AI

Utility-based control (UBC) hasn't been widely adopted for commercial game AI. Some of the reasons for this are that UBC is perceived to be: (1) resource intensive, (2) difficult to design complex behaviours with, and (3) difficult to scale for use in complex environments. This paper investigates these perceptions to see if UBC is suitable for controlling the behaviour of non-player characters in commercial games. The investigation compares agents using a UBC system against two control systems that are more frequently used in commercial games: finite state machines (FSMs), considered a simple control system, and goal-oriented action planning (GOAP), considered a complex control system. We present a case study which suggests that: (1) UBC is more resource intensive than FSMs and less than GOAP; (2) it was reasonably simple to create complex behaviours with UBC; (3) UBC didn't scale as well as FSMs or GOAP for use in complex environments.

- by John Kelleher
- •
- Computer Science, Control system, Feasibility Study, Utility

We present a fully procedural alternative to branching dialogue that is influenced by theories from linguistic pragmatics and technical work in the field of dialogue systems. Specifically, this is a dialogue manager that extends the Talk of the Town framework, in which non-player characters (NPCs) develop and propagate subjective knowledge of the gameworld. While previously knowledge exchange in this framework could only be expressed symbolically, such exchanges may now be rendered as naturalistic conversations between characters. The larger conversation engine currently lacks a player interface, so in this paper we demonstrate our dialogue manager through conversations between NPCs. From an evaluation task, we find that our system produces conversations that flow far more naturally than randomly assembled ones. As a design objective, we have endeavored to make this dialogue manager lightweight and agnostic to its particular application in Talk of the Town; it is our hope that interested readers will consider porting its straightforward design to their own game engines.

- by James Ryan
- •
- Artificial Intelligence, Natural Language Generation, Multiagent Systems, Video Games

In this paper we explore the use of Hierarchical-Task-Network (HTN) representations to model strategic game AI. We will present two case studies. The first one reports on an experiment using HTNs to model strategies for Unreal Tournament® (UT) bots. We will argue that it is possible to encode strategies that coordinate teams of bots in first-person shooter games using

- by hai hoang
- •
- Machine Learning, Game Development, Case Study, Behavior Modeling

Real-time strategy games present an environment in which game AI is expected to behave realistically. One feature of realistic behaviour in game AI is the ability to recognise the strategy of the opponent player. This is known as opponent modeling. In this paper, we propose an approach of opponent modeling based on hierarchically structured models. The top-level of the hierarchy can classify the general play style of the opponent. The bottom-level of the hierarchy can classify specific strategies that further define the opponent’s behaviour. Experiments that test the approach are performed in the RTS game Spring. From our results we may conclude that the approach can be successfully used to classify the strategy of an opponent in the Spring game.

- by Frederik Schadd
- •
- Computer Science, game AI, Structural model, Opponent Modeling

Procedural storytelling offers immense promise for games to offer more reactive narrative experiences that feel more deeply tailored to players' decisions. To date, interactive narrative systems have tended toward either a large emergent possibility space with less focus on narrative structure, or toward greater structure with smaller possibility spaces. In this paper, we introduce Lume, a system for procedural narrative generation that combines the best of these two approaches through a novel combinatorial scene architecture in which storylet scenes are comprised of parameterized node-trees. We detail how the system works and discuss how it moves toward creating reactive interactive narratives that are both dynamic and coherent. CCS CONCEPTS • Human-centered computing → Interactive systems and tools; Interaction design theory, concepts and paradigms; Systems and tools for interaction design; Hypertext / hypermedia.

- by Stacey Mason
- •
- Video Games, Interactive Narrative, Procedural Content Generation, Games

—Multi-thread architectures are the current trends for both PCs (multi-core CPUs and GPUs) and game consoles such as the Microsoft Xbox 360 and Sony Playstation 3. GPUs (Graphics Processing Units) have evolved into extremely powerful and flexible processors, allowing its use for processing different data. This advantage can be used in game development to optimize the game loop. As reported in the literature, GPGPUs have been used in processing some steps of the game loop, while most of the game logic is still processed by the CPU. This proposal differs by presenting an architecture designed to process practically the entire game loop using the GPU. Two test cases, a crowd simulation and a 2D game shooter prototype called GpuWars, are presented to illustrate the proposed architecture.

This paper suggests multi-agent systems (MASs) for implementing game artificial intelligence (AI) for video games. One of main hindrances against using MASs technology in video games has been the real-time constraints for frame rendering. In order to deal with the real-time constraints, we introduce an adaptation-oriented approach for maintaining frame rate in acceptable ranges. The adaptation approach is inspired from the level of detail (LoD) technique in 3D graphics. We introduce agent organizations for defining different roles of agents in game AI. The computational requirements of agent roles have been prioritized according to their functional roles in a game. In this way, adapting computational requirements of game AI works as a means for maintaining frame rate in acceptable ranges. The proposed approach has been evaluated through a pilot experiment by using a proof of concept game. The pilot experiment shows that LoD based adaptation allows maintaining frame rate in acceptable ranges and therefore enhancing the quality of service.

- by Ghulam Mahdi
- •
- Adaptation, Level Of Detail (LOD), Organization, game AI

To adapt game difficulty upon game character’s strength, Dynamic Difficulty Adjustment (DDA) and some other learning strategies have been applied in commercial game designs. However, most of the existing approaches could not ensure diversity in results, and rarely attempted to coordinate content generation and behaviour control together. This paper suggests a solution that is based on multi-level swarm model and ecosystem mechanism, in order to provide a more flexible way of game balance control.

- by Arnav Jhala
- •
- Artificial Intelligence, Decision Making, Multi Agent Systems, Design Pattern

Crowds of noncombatants play a large and increasingly recognized role in modern military operations and often create substantial difficulties for the combatant forces involved. However, realistic models of crowds are essentially absent from current military simulations. To address this problem, the authors are developing a crowd simulation capable of generating crowds of noncombatant civilians that exhibit a variety of realistic individual and group behaviors at differing levels of fidelity. The crowd simulation is interoperable with existing military simulations using a standard, distributed simulation architecture. Commercial game technology is used in the crowd simulation to model both urban terrain and the physical behaviors of the human characters that make up the crowd. The objective of this article is to present the design and development process of a simulation that integrates commercially available game technology with current military simulations to generate realistic and believable crowd behavior.

- by Frederic McKenzie
- •
- Psychology, Cognitive Science, Design, Group Behavior

Would it be possible to bring the promise of unlimited re-playability typically reserved for Roguelike games to competitive multiplayer shooters? This paper tries to address this issue by proposing a novel method to dynamically generate maps at run-time almost as soon as players press the Play button, while ensuring the features what players would expect from the genre. The procedures are simple and practically feasible to be employed in actual computer games. In addition, the work experiments the possibility of incorporating asynchronous game-play element into a multiplayer shooter with human imitating bots where the players can let their bot/avatar replace them when they are not around. The algorithms are implemented and evaluated with a playable game. The evaluations prove that playable 3D dynamic maps can be generated in order of seconds using game context data to initialise the parameters of the algorithm. The paper also shows that asynchronous game-play element is a possible feature for consideration in next generation multiplayer shooters.

- by Anand Bhojan
- •
- Procedural Content Generation, game AI, AI for Games

This paper proposes a motion-gaming AI for health promotion that can adapt to the player's behavior change in an effective manner. Through modeling of the player's behavior and predicting of their counteraction, this AI learns how its actions can induce its opponent player to move. The proposed AI aims at suppressing health risks associated with motion gaming, by improving balancedness in use of body segments, as well as at increasing the level of calories consumption.

- by Pujana Paliyawan
- •
- Artificial Intelligence, Games for Health, Motion Detection, Exergaming

We describe and compare several methods for generating game character controllers that mimic the playing style of a particular human player, or of a population of human players, across video game levels. Similarity in playing style is measured through an evaluation framework, that compares the play trace of one or several human players with the punctuated play trace of an AI player. The methods that are compared are either hand-coded, direct (based on supervised learning) or indirect (based on maximising a similarity measure). We find that a method based on neuroevolution performs best both in terms of the instrumental similarity measure and in phenomenological evaluation by human spectators. A version of the classic platform game "Super Mario Bros" is used as the testbed game in this study but the methods are applicable to other games that are based on character movement in space.

- by Juan Ortega
- •
- Neuroevolution, Entertainment Computing, Communication and media Studies, game AI
- by Jason Teo
- •
- Computational Intelligence, Differential Evolution, Artificial Neural Networks, game AI

Classic approaches to game AI require either a high quality of domain knowledge, or a long time to generate effective AI behaviour. These two characteristics hamper the goal of establishing challenging game AI. In this paper, we put forward Monte-Carlo Tree Search as a novel, unified framework to game AI. In the framework, randomized explorations of the search space are used to predict the most promising game actions. We will demonstrate that Monte-Carlo Tree Search can be applied effectively to (1) classic board-games, (2) modern board-games, and (3) video games. *

- by Istvan Szita and +1
- •
- Video Game, Domain Knowledge, Search Space, game AI

Real-time strategy (RTS) games are complex decision domains which require quick reactions as well as strategic planning. In this paper we describe the first RTS game AI tournament, which was held in June 2006, and the programs that... more

- by david tom
- •
- System Design, Real Time, game AI

This paper presents the design of an architecture for narrative games with story-puzzles like classic graphic adventures. The system is able to create new short stories in each session, combining a basic set of narrative elements in an emergent way but maintaining coherency with the storyline of previous sessions. As a test-bed of this proposal we use a simple detective game inspired on the famous Cluedo's characters.

- by Federico Peinado
- •
- Computer Science, Artificial Intelligence, Game studies, Game Design

Open world games create a refreshing gaming experience by providing a dynamic environment with many interactable game systems and characters. These systems require special game artificial intelligence (AI) agents to create an illusion of an authentic, living world. The hypothesis is, By modeling game systems that are suitable for Multi-Agent Reinforcement Learning and Evolutionary Game Theory principles, it is possible to create game AI agents that can act rationally and adaptive to the dynamic environment. Doing so will hypothetically make open-worlds more compelling and immersive by making players think that they are in a world with intelligent living beings that have already existed long before. The focus will be on creating a single system with adaptive human-like game AI agents first, then gradually introducing multiple game systems and real players. Finally, the results of this research will be used in commercial open-world games and its effect will be observed.

- by Ertugrul Akay
- •
- game AI

We adapt popular video games technology for an agent-based crowd simulation in an airport terminal. To achieve this, we investigate the unique traits of airports and implement a virtual crowd by exploiting a scalable layered intelligence technique in combination with physics middleware and a socialforces approach. Our experiments show that the framework runs at interactive frame-rate and evaluate the scalability with increasing number of agents demonstrating navigation behaviour.

- by Patrick Dickinson and +1
- •
- Agent Based, Crowd Simulation, Video Game, Middleware

Real-Time Strategy (RTS) games are well-known for their substantially large combinatorial decision and state spaces, responsible for creating significant challenges for search and machine learning techniques. Exploiting domain knowledge to assist in navigating the expansive decision and state spaces could facilitate the emergence of competitive RTS game-playing agents. Usually, domain knowledge can take the form of expert traces or expert-authored scripts. A script encodes a strategy conceived by a human expert and can be used to steer a search algorithm, such as Monte Carlo Tree Search (MCTS), towards high-value states. However, a script is coarse by nature, meaning that it could be subject to exploitation and poor low-level tactical performance. We propose to perceive scripts as a collection of heuristics that can be parameterized and combined to form a wide array of strategies. The parameterized heuristics mold and filter the decision space in favor of a strategy expressed in terms of parameters. The proposed agent, ParaMCTS, implements several common heuristics and uses NaïveMCTS to search the downsized decision space; however, it requires a preceding manual parameterization step. A genetic algorithm is proposed for use in an optimization phase that aims to replace manual tuning and find an optimal set of parameters for use by EvoPMCTS, the evolutionary counterpart of ParaMCTS. Experimentation results using the µRTS testbed show that EvoPMCTS outperforms several state-of-the-art agents across multiple maps of distinct layouts.

- by Abdessamed Ouessai
- •
- Artificial Intelligence, Evolutionary algorithms, Genetic Algorithms, game AI

One of the key areas for the application of Artificial Intelligence to the game domain is in the design of challenging artificial opponents for human players. Complex simulations such as historical wargames can be seen as natural extensions of classical games where AI techniques such as planning or learning have already proved powerful. Yet the parallel nature of more recent games introduce new levels of complexity which can be tackled at various levels. This paper focuses on the question of finding good representations for the AI design, which implies finding relevant granularities for the various tasks involved, for a popular historical wargame. This work is based on the partially automated use of the rules of the game, as well as some common sense and historical military knowledge, to design relevant heuristics. The resulting gain in representation complexity will help the application of techniques such as Reinforcement Learning.

- by Charles Madeira
- •
- Reinforcement Learning, Common Sense, Artificial Intelligent, Terrain analysis

The growth of the mobile gaming market offers considerable potential for the deployment of engaging and compelling games constructed using AI components and techniques. This paper discusses a rule-based approach for constructing lightweight Game AI systems for deployment on mobile devices. The development environment and the mimosa programming language for constructing Game AI components are outlined. A prototype game of Texas Hold'em Poker implemented using this environment is described. Ideas for future work, including the development of games mentors for deployment on mobile devices are briefly presented.

- by Adrian Gordon
- •
- Mobile Device, Mobile games, Environment and Development, game AI

Developing computer-controlled groups to engage in combat, control the use of limited resources, and create units and buildings in Real-Time Strategy(RTS) Games is a novel application in game AI. However, tightly controlled online commercial game pose challenges to researchers interested in observing player activities, constructing player strategy models, and developing practical AI technology in them. Instead of setting up new programming environments or building a large amount of agent's decision rules by player's experience for conducting real-time AI research, the authors use replays of the commercial RTS game StarCraft to evaluate human player behaviors and to construct an intelligent system to learn human-like decisions and behaviors. A case-based reasoning approach was applied for the purpose of training our system to learn and predict player strategies. Our analysis indicates that the proposed system is capable of learning and predicting individual player strategies, and that players provide evidence of their personal characteristics through their building construction order.

- by Chuen-Tsai Sun
- •
- Artificial Intelligence, Game Theory, Automatic Control, Path planning

Imitation is a powerful mechanism the human brain applies to extend its repertoire of solutions and behaviors suitable to solve problems of various kinds. From an abstract point of view, the major advantage of this strategy is that it reduces the search space of apropriate solutions. In this contribution, we discuss if and how the principle of imitation learning can facilitate the programing of life-like computer game charecters. We present different algorithms that learn from human generated training data and we show that machine learning can be applied on different levels of cognitive abstraction.

- by Gerhard Sagerer
- •
- Proceedings, Human Brain, Imitation Learning, Search Space
- by John Laird
- •
- game AI

Real-time strategy (RTS) games are complex decision domains which require quick reactions as well as strate- gic planning. In this paper we describe the first RTS game AI tournament, which was held in June 2006, and the programs that... more

- by Timothy Furtak and +2
- •
- System Design, Real Time, game AI

The impressive performance of Monte Carlo Tree Search (MCTS) based game-playing agents in high branching-factor domains such as Go, motivated researchers to apply and adapt MCTS to even more challenging domains. Real-time strategy (RTS) games feature a large combinatorial branching factor and a real-time aspect that pose significant challenges to a broad spectrum of AI techniques, including MCTS. Various MCTS enhancements were proposed, such as the combinatorial multi-armed bandit (CMAB) based sampling, state/action abstractions, and machine learning. In this paper, we propose to employ move pruning as a way to improve the performance of MCTS-based agents in the context of RTS games. We describe a class of possibly detrimental player-actions and propose several pruning approaches targeting it. The experimentation results in µRTS indicate that this could be a promising direction.

- by Abdessamed Ouessai
- •
- Video Games, game AI, Monte Carlo Tree Search, AI for Games

This paper proposes a motion gaming AI that encourages players to use their body parts in a well-balanced manner while promoting their enjoyment. The proposed AI uses time series forecasting to predict what actions its opponent human player will perform with respect to a candidate action of the AI, from which result it estimates the amount of movement (momentum) to be produced on each part of the body of the human player against its action. The AI finally selects an action with the goal of making the momentum of body parts on each side of the player body equal. In this AI, a Monte-Carlo Tree Search (MCTS) is employed for candidate action selection and is embedded with a dynamic difficulty adjustment (DDA) mechanism for enhancing enjoyment of the game. Our results offer a contingent evidence that an opponent gaming AI can be used to effectively improve the human player's balance, enjoyment, engrossment, personal gratification while playing the game.

- by Pujana Paliyawan
- •
- Video Games, game AI

The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multilayered architecture named CAse-Based Reinforcement Learner (CARL). It uses a novel combination of Case-Based Reasoning (CBR) and Reinforcement Learning (RL) to achieve transfer while playing against the Game AI across a variety of scenarios in MadRTS TM , a commercial Real Time Strategy game. Our experiments demonstrate that CARL not only performs well on individual tasks but also exhibits significant performance gains when allowed to transfer knowledge from previous tasks.

- by Manu Sharma
- •
- Transfer Learning, game AI, Case Base Reasoning, Layered Architecture

Recently, the complexity of modern, real-time computer games has increased drastically. The need for sophisticated game AI, in particular for Non-Player Characters, grows with the demand for realistic games. Writing consistent, re-useable and efficient AI code has become hard. We demonstrate how modeling game AI at an appropriate abstraction level using an appropriate modeling language has many advantages. A variant of Rhapsody Statecharts is proposed as an appropriate formalism. The Tank Wars game by Electronic Arts (EA) is used to demonstrate our concrete approach. We show how the use of the Statecharts formalism leads quite naturally to layered modeling of game AI and allows modelers to abstract away from choices between, for example, time-slicing and discrete-event time management. Finally, our custom tools are used to synthesize efficient C++ code to insert into the Tank Wars main game loop.

- by Hans Vangheluwe and +1
- •
- Real Time Computing, Modeling Language, Time Management, game AI

- by Abdelkader Gouaich
- •
- Adaptation, Level Of Detail (LOD), Organization, game AI

Games technology has undergone tremendous development. In this article, the authors report the rapid advancement that has been observed in the way games software is being developed, as well as in the development of games content using game engines. One area that has gained special attention is modeling the game environment such as terrain and buildings. This article presents the continuous level of detail terrain modeling techniques that can help generate and render realistic terrain in real time. Deployment of characters in the environment is increasingly common. This requires strategies to map scalable behavior characteristics for characters as well. The authors present two important aspects of crowd simulation: the realism of the crowd behavior and the computational overhead involved. A good simulation of crowd behavior requires delicate balance between these aspects. The focus in this article is on human behavior representation for crowd simulation. To enhance the player experience, the authors present the concept of player adaptive entertainment computing, which provides a personalized experience for each individual when interacting with the game. The current state of game development involves using very small percentage (typically 4% to 12%) of CPU time for game artificial intelligence (AI). Future game AI requires developing computational strategies that have little involvement of CPU for online play, while using CPU's idle capacity when the game is not being played, thereby emphasizing the construction of complex game AI models offline. A framework of such nonconventional game AI models is introduced.

- by Narendra Chaudhari
- •
- Psychology, Cognitive Science, Artificial Intelligence, Genetic Algorithms

This paper describes the 2009 Mario AI Competition, which was run in association with the IEEE Games Innovation Conference and the IEEE Symposium on Computational Intelligence and Games. The focus of the competition was on developing controllers that could play a version of Super Mario Bros as well as possible. We describe the motivations for holding this competition, the challenges associated with developing artificial intelligence for platform games, the software and API developed for the competition, the competition rules and organization, the submitted controllers and the results. We conclude the paper by discussing what the outcomes of the competition can teach us both about developing platform game AI and about organizing game AI competitions. The first two authors are the organizers of the competition, while the third author is the winner of the competition.

This paper describes two different decision tree-based approaches to obtain strategies that control the behavior of bots in the context of the Unreal Tournament 2004. The first approach follows the traditional process existing in commercial videogames to program the game artificial intelligence (AI), that is to say, it consists of coding the strategy manually according to the AI programmer's experience with the aim of increasing player satisfaction. The second approach is based on evolutionary programming techniques and has the objective of automatically generating the game AI. An experimental analysis is conducted in order to evaluate the quality of our proposals. This analysis is executed on the basis of two fitness functions that were defined intuitively to provide entertainment to the player. Finally a comparison between the two approaches is done following the subjective evaluation principles imposed by the "2k bot prize" competition.

- by Jorge Barragán and +1
- •
- Artificial Intelligent, Decision Tree, game AI, Fitness Function

Many modern games provide environments in which agents perform decision making at several levels of granularity. In the domain of real-time strategy games, an effective agent must make high-level strategic decisions while simultaneously controlling individual units in battle. We advocate reactive planning as a powerful technique for building multiscale game AI and demonstrate that it enables the specification of complex, real-time agents in a unified agent architecture. We present several idioms used to enable authoring of an agent that concurrently pursues strategic and tactical goals, and an agent for playing the real-time strategy game StarCraft that uses these design patterns.

- by Peter Mawhorter
- •
- Artificial Intelligence, Decision Making, Multi Agent Systems, Design Pattern

Online learning in commercial computer games allows computer-controlled opponents to adapt to the way the game is being played. As such it provides a mechanism to deal with weaknesses in the game AI, and to respond to changes in human player tactics. We argue that online learning of game AI should meet four computational and four functional requirements. The computational requirements are speed, effectiveness, robustness and efficiency. The functional requirements are clarity, variety, consistency and scalability. This paper investigates a novel online learning technique for game AI called 'dynamic scripting', that uses an adaptive rulebase for the generation of game AI on the fly. The performance of dynamic scripting is evaluated in experiments in which adaptive agents are pitted against a collection of manually-designed tactics in a simulated computer roleplaying game. Experimental results indicate that dynamic scripting succeeds in endowing computer-controlled opponents with adaptive performance. To further improve the dynamic-scripting technique, an enhancement is investigated that allows scaling of the difficulty level of the game AI to the human player's skill level. With the enhancement, dynamic scripting meets all computational and functional requirements. The applicability of dynamic scripting in state-of-the-art commercial games is demonstrated by implementing the technique in the game Neverwinter Nights. We conclude that dynamic scripting can be successfully applied to the online adaptation of game AI in commercial computer games.

- by Eric Postma
- •
- Cognitive Science, Reinforcement Learning, Machine Learning, Online Learning
- by Pierre Bessiere
- •
- Machine Learning, game AI, Bayesian Modeling
- by Daniel Livingstone
- •
- Evaluation, Machine Intelligence, Turing Test, game AI
- by Robert Amor and +1
- •
- Software Architecture, Collision detection, game AI

Real-time strategy games present an environment in which game AI is expected to behave realistically. One feature of realistic behaviour in game AI is the ability to recognise the strategy of the opponent player. This is known as opponent modeling. In this paper, we propose an approach of opponent modeling based on hierarchically structured models. The top-level of the hierarchy can classify the general play style of the opponent. The bottom-level of the hierarchy can classify specific strategies that further define the opponent's behaviour. Experiments that test the approach are performed in the RTS game Spring. From our results we may conclude that the approach can be successfully used to classify the strategy of an opponent in the Spring game.

- by Frederik Schadd
- •
- game AI, Structural model, Opponent Modeling, Game On

- by hai hoang
- •
- Machine Learning, Game Development, Case Study, Behavior Modeling

- by juan ortega
- •
- Neuroevolution, Entertainment Computing, Communication and media Studies, game AI

- by Chuen-Tsai Sun
- •
- Artificial Intelligence, Game Theory, Automatic Control, Path planning

Although a number of multi-objective evolutionary algorithms (MOEAs) have been proposed over the last two decades, very few studies have utilized MOEAs for game agent synthesis. Recently, we have suggested a co-evolutionary implementation using the Pareto Evolutionary Programming (PEP) algorithm. This paper describes a series of experiments using PEP for evolving artificial neural networks (ANNs) that act as game-playing agents. Three systems are compared: (i) a

- by Jason Teo
- •
- Differential Evolution, Intelligent Agent, game AI, Game Playing

Massively Multiplayer Online Role-Playing Games (MMORPGs) typically use a handful of static conventions for involving players in stories, such as predefined quest or story paths (a quest or story path is one in which the user experiences a sequence of related quests that must be accomplished in a particular order). Beyond the work done in MMORPGs there has been strong

- by James Pita and +1
- •
- Interactive Narrative, User eXperience, System Architecture, game AI

Computer games are attracting increasing interest in the Artificial Intelligence (AI) research community, mainly because games involve reasoning, planning and learning [Fürnkranz 2007]. One area of particular interest in the last years is the creation of adaptive game AI. Adaptive game AI is the implementation of AI in computer games that holds the ability to adapt to changing circumstances, i.e., to exhibit adaptive behavior during the play. This kind of adaptation can be created using Machine Learning techniques, such as neural networks, reinforcement learning and bioinspired methods. In order to learn online, a system needs to overcome the main difficulties imposed by games: processing time and memory requirements. Learning in a game needs to be fast and the memory available is usually not enough to store a large number of training examples to a traditional Machine Learning technique. In this context, methods for mining data streams seem to be a natural approach. Data streams are, by definition, sequences of training examples that arrive over time [Gama and Rodrigues 2009]. In the data stream scenario, algorithms are usually incremental and capable of adapting the decision model when a change in the distribution of the training examples is detected. One particularly interesting algorithm for mining data streams is the Very Fast Decision Tree (VFDT) [Domingos and Hulten 2000]. VFDTs are incremental decision trees designed specifically to meet the data stream problem requirements. In this paper, we analyse the use of VFDTs in the task of learning in a Computer RolePlaying Game context. First, we simulate data from manually designed tactics for a Computer Role-Playing Game, based on Spronck's static tactics [Spronck 2005], and test the suitability of VFDT to rapid learn these tactics. Afterwards, we conduct an experiment in order to simulate a data stream of examples where changes of tactics occur over time, and analyse how VFDT and some of its variations respond to these changes in the target concept.

- by Joao Gama
- •
- Computer Science, Reinforcement Learning, Machine Learning, Data Mining