Software agents are well-suited to assisting users with routine, repetitive, and time-consuming tasks in various educational environments. In order to achieve complex tasks effectively, humans and agents sometimes need to work together. However, some issues in human agent interaction have not been solved properly, such as delegation, trust and privacy. The agent research community has focused on technologies for constructing autonomous agents and techniques for collaboration among agents. Little attention has been paid to supporting interactions between humans and agents. p* The objectives of this research are to investigate how easy it might be for a user to program his/her agent, how users behave when given the ability to program their agents, whether access to necessary help resources can be improved, and whether such a system can facilitate collaborative learning. Studying users concerns about their privacy and how an online learning environment can be built to protect users privacy are also interesting issues to us. <p>In this thesis two alternative systems were developed for programmable agents in which a human user can define a set of rules to direct an agents activities at execution time. The systems were built on top of a multi-agent collaborative learning environment that enables a user to program his or her agent to communicate with other agents and to monitor the activities of other users and their agents. These systems for end user programmable agents were evaluated and compared. The result demonstrated that an end-user programming environment is able to meet users individual needs on awareness information, facilitate the information exchange among the users, and enhance the communication between users within a virtual learning environment. This research provides a platform for investigating concerns over user privacy caused by agent programmability.

Software agents are well-suited to assisting users with routine, repetitive, and time-consuming tasks in various educational environments. In order to achieve complex tasks effectively, humans and agents sometimes need to work together. However, some issues in human agent interaction have not been solved properly, such as delegation, trust and privacy. The agent research community has focused on technologies for constructing autonomous agents and techniques for collaboration among agents. Little attention has been paid to supporting interactions between humans and agents. p* The objectives of this research are to investigate how easy it might be for a user to program his/her agent, how users behave when given the ability to program their agents, whether access to necessary help resources can be improved, and whether such a system can facilitate collaborative learning. Studying users concerns about their privacy and how an online learning environment can be built to protect users privacy are also interesting issues to us. <p>In this thesis two alternative systems were developed for programmable agents in which a human user can define a set of rules to direct an agents activities at execution time. The systems were built on top of a multi-agent collaborative learning environment that enables a user to program his or her agent to communicate with other agents and to monitor the activities of other users and their agents. These systems for end user programmable agents were evaluated and compared. The result demonstrated that an end-user programming environment is able to meet users individual needs on awareness information, facilitate the information exchange among the users, and enhance the communication between users within a virtual learning environment. This research provides a platform for investigating concerns over user privacy caused by agent programmability.

Virtual Software Corporations (VSCs) are a novel and important organisational form for large-scale software development. The increased complexity of this development environment requires the use of tools to support human actors in undertaking their tasks, which in turn require modelling solutions able to capture the VSC specific issues. One of the key aspects identified for software development in a VSC setting is the need to support co-ordination. One approach in the development of support for coordination in heterogeneous environments in respect to processes and support tools, such as VSCs, is the use of commitment management. The purpose of this thesis is to define a formalism suitable for capturing and managing commitments, as a means to support co-ordination. This is done by first analysing existing VSCs, and determining the requirements for co-ordination support. Consequently a formalism is defined to address the requirements. The formalism is based on a commitment modelling approach and deontic logic, a modal logic, which is used to manage the commitments. The defined formalism is the basis of a prototype support system, which is used for testing and evaluating. The evaluation has focused on identifying the level of support provided for the initial requirements. To this end three process examples have been used: the initial case study, the study of an independent VSC and the example of a desired process for software configuration management.The results indicate that the formalism, through the use of the prototype system, is able to represent and to manage commitments, as the most important issues in coordinating VSC software development. Thus it has a significant contribution as a modelling approach and it was shown to be applicable to realistic process scenarios.

No description available.

No description available.

No description available.

No description available.

No description available.

Previous attempts at implementing bots for the classic roguelike game NetHack have been hindered by many problems related to its complexity and console-based interface. The framework implemented as part of this work solves the problem of interfacing with the game and provides a programmer-friendly API for the Java and Clojure programming languages. It enables programming sophisticated bots using the provided model of the game world, a library of possible actions and utilities for various aspects of the game. The framework uses elements of functional and logic programming and doesn't require modifications of the game. Also described is an implementation of the first NetHack bot capable of winning the game. Powered by TCPDF (www.tcpdf.org)

Degree: Master of Science in Engineering Department: Engineering / Multi-Agent Systems are becoming a popular paradigm for many engineering applications. However, there is still much research to be performed in this fast growing field. In this thesis, the effect of learning in multi-agent systems on communication and collaboration between agents is investigated. This research focuses on agents learning local cooperative behaviour from a centralised agent, as well as using learning to reduce the amount of communication between agents that use negotiation to achieve their goals. A simple test problem is formulated in MATLAB. The effect of learning is clearly seen to reduce the amount of communication between agents by up to 50%, while still maintaining cooperative behaviour. The agents are also demonstrated to learn to a large degree cooperative local behaviour from a central system.