Multi-agent systems are increasingly popular for modeling distributed environments that are highly complex and dynamic such as e-commerce, smart buildings, and smart grids. Often in open multi-agent systems, agents interact with other agents to meet their own goals. Trust is considered significant in multi-agent systems to make interactions effectively, especially when agents cannot assure that potential partners share the same core beliefs about the system or make accurate statements regarding their competencies and abilities. This work describes a trust model that augments fuzzy logic with Q-learning, and a suspension technique to help trust evaluating agents select beneficial trustees for interaction in uncertain, imprecise, and the dynamic multi-agent systems. Q-Learning is used to evaluate trust on the long term, fuzzy inferences are used to aggregate different trust factors and suspension is used as a short-term response to dynamic changes. The performance of the proposed model is evaluated using simulation. Simulation results indicate that the proposed model can help agents select trustworthy partners to interact with. It has a better performance compared to some of the popular trust models in the presence of misbehaving interaction partners. When interactions are based on trust, trust establishment mechanisms can be used to direct trustees, instead of trustors, to build a higher level of trust and have a greater impact on the results of interactions. This work also describes a trust establishment model for intelligent agents using implicit feedback that goes beyond trust evaluation to outline actions to guide trustees (instead of trustors). The model uses the retention of trustors to model trustors’ behaviours. For situations where tasks are multi-criteria and explicit feedback is available, we present a trust establishment model that uses a multi-criteria approach to help trustees to adjust their behaviours to improve their perceived trust and attract more interactions with trustors. The model calculates the necessary improvement per criterion when only a single aggregated satisfaction value is provided per interaction, where the model attempts to predicted both the appropriate value per criteria and its importance. Then we present a trust establishment model that integrates the two major sources of information to produce a comprehensive assessment of a trustor’s likely needs in multi-agent systems. Specifically, the model attempts to incorporates explicit feedback, and implicit feed-back assuming multi-criteria tasks. The proposed models are evaluated through simulation, we found that trustees can enhance their trustworthiness, at a cost, if they tune their behaviour in response to feedback (explicit or implicit) from trustors. Using explicit feedback with multi-criteria tasks, trustees can emphasize on important criterion to satisfy need of trustors. Trust establishment based on explicit feedback for multi-criteria tasks, can result in a more effective and efficient trust establishment compared to using implicit feedback alone. Integrating both approaches together can achieve a reasonable trust level at a relatively lower cost.

This thesis relates to the usage of trust modelling in multi-agent systems - environments in which there are interacting software agents representing various users (for example, buyers and sellers exchanging products and services in an electronic marketplace). In such applications, trust modelling may be crucial to allow one group of agents (in the e-commerce scenario, buyers) to make effective decisions about which other agents (i.e., sellers) are the most appropriate partners. A number of existing multi-agent trust models have been proposed in the literature to help buyers accurately select the most trustworthy sellers. Our contribution is to propose several modifications that can be applied to existing probabilistic multi-agent trust models. First, we examine how the accuracy of the model can be improved by limiting the network to a portion of the population consisting of the most trustworthy agents, such that the less trustworthy contributions of the remaining agents can be ignored. In particular, we explore how this can be accomplished by either setting a maximum size for a buyer's advisor network or setting a minimum trustworthiness threshold for agents to be accepted into that advisor network, and develop methods for appropriately selecting the values to limit the network size. We demonstrate that for two models, both the Personalized Trust Model (PTM) developed by Zhang as well as TRAVOS, these approaches will yield significant improvements to the accuracy of the trust model, as opposed to using an unrestricted advisor network. Our final proposed modification is to use an advisor referral system in combination with one of the network-limiting approaches. This would ensure that if a particular agent within the advisor network had not met a specified level of experience with the seller under consideration, it could be replaced by another agent that had greater experience with that seller, which should in turn allow for a more accurate modelling of the seller's trustworthiness. We present a particular approach for replacing advisors, and show that this will yield additional improvements in trust-modelling accuracy with both PTM and TRAVOS, especially if the limiting step were such that it would yield a very small advisor network. We believe that these techniques will be very useful for trust researchers seeking to improve the accuracy of their own trust models, and to that end we explain how other researchers could apply these modifications themselves, in order to identify the optimal parameters for their usage. We discuss as well the value of our proposals for identifying an "optimal" size for a social network, and the use of referral systems, for researchers in other areas of artificial intelligence.

This thesis relates to the usage of trust modelling in multi-agent systems - environments in which there are interacting software agents representing various users (for example, buyers and sellers exchanging products and services in an electronic marketplace). In such applications, trust modelling may be crucial to allow one group of agents (in the e-commerce scenario, buyers) to make effective decisions about which other agents (i.e., sellers) are the most appropriate partners. A number of existing multi-agent trust models have been proposed in the literature to help buyers accurately select the most trustworthy sellers. Our contribution is to propose several modifications that can be applied to existing probabilistic multi-agent trust models. First, we examine how the accuracy of the model can be improved by limiting the network to a portion of the population consisting of the most trustworthy agents, such that the less trustworthy contributions of the remaining agents can be ignored. In particular, we explore how this can be accomplished by either setting a maximum size for a buyer's advisor network or setting a minimum trustworthiness threshold for agents to be accepted into that advisor network, and develop methods for appropriately selecting the values to limit the network size. We demonstrate that for two models, both the Personalized Trust Model (PTM) developed by Zhang as well as TRAVOS, these approaches will yield significant improvements to the accuracy of the trust model, as opposed to using an unrestricted advisor network. Our final proposed modification is to use an advisor referral system in combination with one of the network-limiting approaches. This would ensure that if a particular agent within the advisor network had not met a specified level of experience with the seller under consideration, it could be replaced by another agent that had greater experience with that seller, which should in turn allow for a more accurate modelling of the seller's trustworthiness. We present a particular approach for replacing advisors, and show that this will yield additional improvements in trust-modelling accuracy with both PTM and TRAVOS, especially if the limiting step were such that it would yield a very small advisor network. We believe that these techniques will be very useful for trust researchers seeking to improve the accuracy of their own trust models, and to that end we explain how other researchers could apply these modifications themselves, in order to identify the optimal parameters for their usage. We discuss as well the value of our proposals for identifying an "optimal" size for a social network, and the use of referral systems, for researchers in other areas of artificial intelligence.