Search By Subject

Networks are enablers, allowing the diffusion of valuable information. But just as a network is a conduit for valuable information, so it is for misinformation. One major challenge in a networked environment is limiting the spread of misinformation. ...

Machine learning algorithms in the field of economics and game theory usually involve computing an intermediate valuation function from data samples and using this approximate function to compute desired solution concepts. This approach has several ...

This paper summarises the main results obtained within my Ph.D. thesis where I studied argumentation from the point of view of dynamics, focusing, in particular, in the ability to manage the evolution of information. I considered different aspects of ...

Sampling-based approaches in Reinforcement Learning (RL) typically involve learning or maintaining distributions. While many elegant algorithms were proposed in literature, most methods involve prior assumptions of the underlying distributions (eg. ...

Long-term autonomy requires autonomous systems to adapt as their capabilities no longer perform as expected. To achieve this, a system must first be capable of detecting such changes. In this extended abstract, a specification for BDI autonomous agents ...

Trust is an important element of any interaction, but especially when we are interacting with a piece of technology which does not think like we do. Therefore, AI systems need to understand how humans trust them, and what to do to promote appropriate ...

Most prior works on MARL seek to implement intra-agent complex interactions by explicitly communicating agent actions. However, there have only been a few efforts that examine emergence as arising from complex 'social' interactions or relations based on ...

Navigating amongst pedestrians is a very complex task for an autonomous agent. Not only must the agent understand traffic rules and navigate safely, but it must also act in a way that obeys social norms and does not interfere with other pedestrians. ...

We generalise liquid democracy, a voting model where an agent can either vote on an issue or delegate to another agent who votes on their behalf. As delegations are transitive, delegates can choose to vote directly or to delegate their votes further. ...

Coalition formation and Schelling segregation are important scenarios in algorithmic game theory. While the former considers the strategic behavior of agents gathering in coalitions, the latter is a setting in which agents of two groups seek to surround ...

My thesis will study the intersection of social choice and machine learning, with a focus on recent or under-explored social choice paradigms, such as liquid democracy, and how social choice and ML can benefit each other. My initial results show the ...

Conversational agents have been widely adopted in dialogue systems for various business purposes. Many existing conversational agents are rule-based and require significant human intervention to adapt the knowledge and conversational flow. In this paper,...

Artificial intelligence (AI) planning models play an important role in decision support systems for disaster management e.g. typhoon contingency plan development. However, constructing an AI planning model always requires significant amount of manual ...

Agents can individually devise plans and coordinate to achieve common goals. Methods exist to factor planning problems into separate tasks and distribute the plan synthesis process, while reducing the overall planning complexity. Merging distributedly ...

Value alignment is a crucial aspect of ethical multiagent systems. An important step toward value alignment is identifying values specific to an application context. However, identifying context-specific values is complex and cognitively demanding. To ...

This paper describes a demonstration setup that integrates cognitive agents with the latest W3C standardization efforts for the Web of Things (WoT). The conceptual foundations of the implemented system are the integration of cognitive agent abstractions ...

In recent years, machine learning (ML) models have been successfully applied in a variety of real-world applications. However, they are often complex and incomprehensible to human users. This can decrease trust in their outputs and render their usage in ...

Modeling vessel movement in a maritime environment is an extremely challenging task given the complex nature of vessel behavior. Several existing multiagent maritime decision making frameworks require access to an accurate traffic simulator. We develop ...

We present an extension of the organizational model and infrastructure adopted in JaCaMo, that explicitly encompasses the notion of exception. We propose an exception handling mechanism for organization management in multi-agent systems. This mechanism ...

In this work, we propose a framework that enables a human to teach a robot a new task by interactively providing it with unlabeled instructions. We ground the meaning of instruction signals in the task-learning process, and use them simultaneously for ...