Research Interests:
Research Interests:
In platform videogames, players are frequently tasked with solving medium-term navigation problems in order to gather items or powerups. Artificial agents must generally obtain some form of direct experience before they can solve such... more
In platform videogames, players are frequently tasked with solving medium-term navigation problems in order to gather items or powerups. Artificial agents must generally obtain some form of direct experience before they can solve such tasks. Experience is gained either through training runs, or by exploiting knowledge of the game's physics to generate detailed simulations. Human players, on the other hand, seem to look ahead in high-level, abstract steps. Motivated by human play, we introduce an approach that leverages not only abstract "skills", but also knowledge of what those skills can and cannot achieve. We apply this approach to Infinite Mario, where despite facing randomly generated, maze-like levels, our agent is capable of deriving complex plans in real-time, without relying on perfect knowledge of the game's physics.
Research Interests:
Any computer game with a strong story has difficulty balancing the tension between narrative and agency. Strong narrative usually results in weak agency, and strong agency can weaken narrative structure. Narrative improvisation, adapting... more
Any computer game with a strong story has difficulty balancing the tension between narrative and agency. Strong narrative usually results in weak agency, and strong agency can weaken narrative structure. Narrative improvisation, adapting the story based on player reactions, is a difficult task for a game designer. Narrative improvisation, however, is regularly practised by the human game masters (GMs) of tabletop roleplaying games. As the first stage of building a game master agent (GMA), this paper examines the moment in which GMs decide if and how to alter their storyline due to player action. GMs were interviewed to discover their reactions when players make unexpected choices. Ten themes emerged from analysis of the interviews, we examined these themes to determine the thought processes that took place in the GMs’ minds, and we represented the processes as flow charts. These decision charts are a first step in the construction of a GMA that could assist in the development of more responsive interactive narrative in computer games.
Research Interests:
Social simulation often concerns the behaviour of humans interacting within some system. Simulation applications are increasingly requiring more realistic and complex human modelling, than reactive rules. We suggest that the established... more
Social simulation often concerns the behaviour of humans interacting within some system. Simulation applications are increasingly requiring more realistic and complex human modelling, than reactive rules. We suggest that the established Belief Desire Intention (BDI) approach to modelling cognitive agents, can usefully be applied to modelling humans in social simulations. Traditional social science resources can be used to develop models of human decision making and behaviour that can be represented directly in the BDI programming paradigm. Coupling BDI systems with Agent Based Modelling and Simulation (ABMS) systems, one can create powerful simulations that can be used for a range of analysis, training and community education purposes.
Research Interests:
Research Interests:
Fault identification using the emitted mechanical noise is becoming an attractive field of research in a variety of industries. It is essential to rank acoustic feature integration functions on their efficiency to classify different types... more
Fault identification using the emitted mechanical noise is becoming an attractive field of research in a variety of industries. It is essential to rank acoustic feature integration functions on their efficiency to classify different types of sound for conducting a fault diagnosis. The Mel frequency cepstral coefficient (MFCC) method was used to obtain various acoustic feature sets in the current study. MFCCs represent the audio signal power spectrum and capture the timbral information of sounds. The objective of this study is to introduce a method for the selection of statistical indicators to integrate the MFCC feature sets. Two purpose-built audio datasets for squeak and rattle were created for the study. Data were collected experimentally to investigate the feature sets of 256 recordings from 8 different rattle classes and 144 recordings from 12 different squeak classes. The support vector machine method was used to evaluate the classifier accuracy with individual feature sets. T...
Research Interests:
Research Interests:
Research Interests:
In this paper we describe an approach for developing an intelligent game master (GM) for computer role-playing games. The role of the GM is to set up the game environment, manage the narrative ow and enforce the game rules whilst keeping... more
In this paper we describe an approach for developing an intelligent game master (GM) for computer role-playing games. The role of the GM is to set up the game environment, manage the narrative ow and enforce the game rules whilst keeping the players engaged. Our approach is to use the popular Belief-Desire-Intention (BDI) model of agents to developing a GM. We describe the process for creating such a GM and how we implemented a prototype of it for a scenario in the Neverwinter Nights (NWN) game. We describe the evaluation of our prototype with human participants who played the chosen NWN scenario both with and without the BDI GM. The comparison survey completed by the participants shows that the system with the BDI GM was the clear winner with respect to game replayability, flexibility, objective setting and overall interest; thus, validating our hypothesis that a BDI GM will provide game players with a better gaming experience.
Research Interests:
In this paper we propose a novel application of reinforcement learning to the area of auditory neural stimulation. We aim to develop a simulation environment which is based off real neurological responses to auditory and electrical... more
In this paper we propose a novel application of reinforcement learning to the area of auditory neural stimulation. We aim to develop a simulation environment which is based off real neurological responses to auditory and electrical stimulation in the cochlear nucleus (CN) and inferior colliculus (IC) of an animal model. Using this simulator we implement closed loop reinforcement learning algorithms to determine which methods are most effective at learning effective acoustic neural stimulation strategies. By recording a comprehensive set of acoustic frequency presentations and neural responses from a set of animals we created a large database of neural responses to acoustic stimulation. Extensive electrical stimulation in the CN and the recording of neural responses in the IC provides a mapping of how the auditory system responds to electrical stimuli. The combined dataset is used as the foundation for the simulator, which is used to implement and test learning algorithms. Reinforcem...
Research Interests: Computer Science, Algorithms, Biomedical Engineering, Reinforcement Learning, Machine Learning, and 15 moreMedicine, Learning, Neural Engineering, Humans, Brain Computer Interfaces, Animals, Reinforcement, Cochlear Implants, Clinical Sciences, Rats, prosthesis Design, Neurosciences, Inferior Colliculus, Cochlear Nucleus, and Electric stimulation
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This paper describes the architecture and the implementation of the SAMIR (Scenographic Agents Mimic Intelligent Reasoning) system, designed to implement 3D conversational agents. SAMIR uses an XCS classifier system to learn natural... more
This paper describes the architecture and the implementation of the SAMIR (Scenographic Agents Mimic Intelligent Reasoning) system, designed to implement 3D conversational agents. SAMIR uses an XCS classifier system to learn natural facial postures to be shown by the agents, during their dialogues with users. An administration program can be run by agent administrators in order to fine-tune the agent knowledge base and emotive responses. It results in a flexible approach to dialogue and facial expressions management, fitting the needs of different web applications such as e-shops or digital libraries.
Research Interests:
Extensive simulation of sensory perception for NPCs (Non Playing Characters) or bots in 3D games has been quite rare if not absent until recently. However, a few games have proven that proper simulation of senses can lead to inter- esting... more
Extensive simulation of sensory perception for NPCs (Non Playing Characters) or bots in 3D games has been quite rare if not absent until recently. However, a few games have proven that proper simulation of senses can lead to inter- esting and novel gameplay, and it is likely that the trend towards more sophisticated simulation will continue. In this paper we analyze the existing techniques to simulate virtual senses, highlight their weaknesses and propose some ideas to improve over the main existing approaches. The work presented here is part of an ongoing research on 3D learn- ing characters, funded by the RMIT Emerging Researchers Grant.
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
In this paper, an investigation is conducted on the security issues in massive multiplayer games. A taxonomy framework for online cheating is provided. Under this proposed framework, online cheating is classified and state of the art... more
In this paper, an investigation is conducted on the security issues in massive multiplayer games. A taxonomy framework for online cheating is provided. Under this proposed framework, online cheating is classified and state of the art counter‐cheating techniques are analysed with emphasis on attacks that pose a considerable challenge to the security of massive multiplayer online games. Copyright © 2008 John Wiley & Sons, Ltd.
Research Interests:
The terms agent, intelligent agent and 3D agent are becoming more and more frequently used in literature. A key issue in the web community is that a web site must be equipped with a virtual agent able to support users in a natural way.... more
The terms agent, intelligent agent and 3D agent are becoming more and more frequently used in literature. A key issue in the web community is that a web site must be equipped with a virtual agent able to support users in a natural way. Following this trend, we decided to ...
Research Interests: Information Systems, Applied Mathematics, Computer Science, Computer Animation, Genetic Algorithms, and 14 moreFacial expression, Intelligent Agents, Genetic Algorithm, Intelligent Agent, IT adoption, Web site, User profile, User Profiling, World Wide Web, Facial Animation, Learning System, Object Oriented, Web community, and Virtual agent
The rapid evolution of Internet services has led to a constantly increasing number of Web sites and to an increase in the available information. The main challenge is to support Web users in order to facilitate navigation through Web... more
The rapid evolution of Internet services has led to a constantly increasing number of Web sites and to an increase in the available information. The main challenge is to support Web users in order to facilitate navigation through Web sites and to improve searching among the extremely large Web repository, such as digital libraries, online product catalogues, or other generic information sources. The complexity of today's services could be lowered by means of proactive support or advice from the system. The proactiveness could be achieved ...
Research Interests:
Research Interests:
... Fabio Abbattista, Department of Computer Science of the University of Bari, Italy. Marco Degemmis, Oriana Licchelli, Pasquale Lops, Fabio Zambetta, Department of Computer Science, University of Bari, Italy. 2003 Article.... more
... Fabio Abbattista, Department of Computer Science of the University of Bari, Italy. Marco Degemmis, Oriana Licchelli, Pasquale Lops, Fabio Zambetta, Department of Computer Science, University of Bari, Italy. 2003 Article. Bibliometrics. ...
Research Interests:
Abstract. The recent evolution of e-commerce emphasized the need for more and more receptive services to the unique and individual requests of users. Personalization became an important business strategy in Business to Consumer commerce,... more
Abstract. The recent evolution of e-commerce emphasized the need for more and more receptive services to the unique and individual requests of users. Personalization became an important business strategy in Business to Consumer commerce, where a user explicitly wants the e-commerce site to consider her own information such as preferences in order to improve access to relevant products. In this work, we present a personalization component that uses supervised machine learning to induce a classifier able to discriminate between ...