For autonomous agents and services to cooperate and interact in multi-agent environments they require well-defined protocols. A multitude of protocol languages for multi-agent systems have been proposed in the past, but they have mostly remained theoretical or have limited prototypical implementations. This work proposes a practical realisation of a general framework for defining dialogue-based bilateral interaction protocols which supports arbitrary agent-based interactions. Crucially, this work is tightly integrated with a modern framework for the creation of autonomous agents and multi-agent systems, making it possible to go from protocols' specification to their implementation and usage by agents, and enables evaluation of protocols' effectiveness and applicability in real-world use cases.

The Internet and the services delivered via it are increasingly centralised on a few monopolistic platforms. Today's web frameworks are conceived to cater for increasing returns to scale and winner-takes-all business models with a built-in asymmetry between users and services. Existing multi-agent and agent architectures have seen no significant adoption outside niche applications. We propose a novel agent framework which is designed to allow for a decentralised digital economy to manifest where each individual and organisation is represented by an autonomous economic entity with its own agency. The framework bridges the old and new web and employs distributed ledger technologies as core parts of its construction. We introduce the framework, discuss the performance characteristics of its current implementation and demonstrate several application areas.

In this demonstration, we introduce a system that facilitates trading agent competitions. Competitions mirror a Walrasian Exchange Economy. Each agent is endowed with a set of digital assets and preferences over them. Agents then trade these assets with each other to increase their respective utilities. They negotiate one-on-one to arrive at an optimal trade, and if successful, settle their transaction trustlessly on an emulated permissionless blockchain. This system is a precursor to a trading platform for digital assets and crypto-tokens in which agents trade on behalf of their users.

The user experience of interacting with distributed ledger technologies (DLT) is fraught with excessive complexity, high risk and unintuitive processes. Moreover, smart contracts deployed in these systems are restricted to being reactive. These limitations have negative implications on user adoption and prevent DLTs from being general purpose. We introduce a framework for the development of Autonomous Economic Agents (AEAs), software agents that act autonomously and pursue an economic goal, and demonstrate how AEAs complement existing decentralised ledgers as a second layer technology. In particular, the framework enables a simplified user experience through automation, supports modularisation and reuse of complex decision making and machine learning capabilities, and allows for proactive behaviour facilitating autonomy. We demonstrate these gains in the context of a specific use-case, a multi-agent trading system modelling a Walrasian Exchange Economy populated by a number of agents trading a basket of tokens.

Real-world transportation networks provide rich and complex environments, well-suited to the deployment of multi-agent systems. In this demonstration, we simulate a population of electric vehicles making a journey between two cities. The challenge for the vehicles lies in making decisions of how best to recharge their batteries using the small number of charging stations that are available on their route. We investigate several scenarios that use a combination of conventional planning techniques alongside automated negotiation, and evaluate their effects on the efficiency of the system.

This thesis provides a formal treatment of the utilisation of enthymemes in dialogical settings, and thus contributes to the formalisation of a key argumentative practice ubiquitous in real world dialogues. The underlying argumentation formalism of our work is ASPIC+, a general framework for structured argumentation which is shown to capture existing systems for argumentation based reasoning. Due to ASPIC+’s lack of support for enthymemes, we modify the ASPIC+ framework so as to enable representation of a broad range of argumentative structures, including arguments and enthymemes. We formalise how an agent i can utilise its model of another agent j’s beliefs and arguments, in order to construct enthymemes from its arguments to send to j, while attempting to ensure that j is capable of reconstructing the original arguments from their respective enthymemes. We then formally define the process of reconstructing the argument from which a received enthymeme was originally constructed, similarly using agents’ models of each others’ beliefs and arguments. We define mechanisms for constructing and maintaining an agent’s model of another agent’s beliefs and arguments. The mechanisms are based on agents’ dialogical exchanges, as well as their quantitatively measured like-mindedness. The latter harnesses the notion that agents in the environment are distributed in groups and communities that are formed on the basis of agents’ intrinsic and extrinsic properties. We then present a general framework for argumentation based dialogue. The framework formalises core elements that are common amongst existing dialogue systems while abstracting away from the details that restricts it to particular systems or specific dialogue types. To illustrate its generality, the framework is instantiated to capture existing dialogue systems, each for a different dialogue type. The framework is then instantiated to represent a system for a new dialogue type, called resolution. Resolution dialogues are designed to be easily embedded within other dialogues of potentially differing types, and enable their participants to reconstruct enthymemes in dialogues. We then show that

This paper proposes mechanisms for agents to model other agents' beliefs and arguments, thus enabling agents to anticipate their interlocutors' arguments in dialogues, which in turn facilitates strategising and the use of enthymemes. In contrast with existing works on "opponent modelling" that treat arguments as abstract entities, the likelihood that an interlocutor can construct an argument is derived from the likelihoods that it possesses the beliefs required to construct the argument. We therefore address how a modelling agent can quantify the certainty that its interlocutor possesses beliefs, based on the modeller's previous dialogues, and the membership of its interlocutor in communities.(2)

This paper proposes mechanisms for agents to model other agents' arguments, so that modelling agents can anticipate the likelihood that their interlocutors can constructs arguments in dialogues. In contrast with existing works on "opponent modelling" which treat arguments as abstract entities, the likelihood that an agent can construct an argument is derived from the likelihoods that it possesses the beliefs required to construct the argument. We therefore also address how a modeller can quantify the certainty that its interlocutor possesses beliefs based on previous dialogues, and membership of interlocutors in communities.

Enthymemes, arguments with incomplete structure, are a ubiquitous feature of human communication and argumentation. This paper proposes a way of representing enthymemes and arguments within the ASPIC+ framework, and how enthymemes are constructed based on estimates of shared knowledge. It then proposes a framework in which agents are capable of constructing a model of other agent’s knowledge.

The rapid advancements in the semantic web technologies has enabled personalised learning based on learnerâ??s characteristics in the learning process. We have implemented a Personalised Adaptive e-Learning system (onto-PAdeL) which uses an ontological approach in design-ing learnersâ?? models. Thus, this paper focuses on describing our approach for modelling learners based on their charac-teristics such as abilities, learning style(s), prior knowledge and preferences. The system uses Item Response Theory (IRT) for calculating learnerâ??s abilities. The learning style can be represented according to different theories, each of which supports personalisation in different ways. We show that using ontologies for learner modelling, in addition to many different benefits, enables reasoning for adaptive learning.

The rapid advancements in e-Learning technology enable each learner to have his/her own learning process based on his/her characteristics - this is called personalisation. Furthermore, recent developments in the field of semantic modelling have led to a renewed attention with focus on ontology-based e-learning systems. This paper describes learners' model ontology as a stage for creating personalised e-Learning systems based on learner's abilities, learning styles, prior knowledge and preferences. The learning style can be represented according to different models to support personalisation in different ways. User profile data is collected when the learner registers to the system and will be updated during the learning process. The system also uses Item Response Theory (IRT) for calculating learner's abilities in order to be more accurate.