We work on various topics in agents and multiagent systems, mostly related to reasoning about interaction, whether this means modelling other agents, trying to resolve conflicts among interacting agents or learning what governs other's behaviour.

The following visualisation shows work done by members of the group along two critical dimensions, cooperative vs. adversarial and single-agent vs. multi-agent. We've attempted to capture similarities between different themes by proximity to the extent that this is possible in a two-dimensional map. Below the map you will find descriptions of individual research projects (feature not available yet).


In everyday life, humans exhibit strong skills in resolving communication problems by re-negotiating what they mean. Modern-day computational systems, however, are lacking in resilience and robustness in this respect. Whenever different components with different vocabularies and models of meaning interact within distributed, open enviroments, they have to rely on their human designers’ abilities to resolve problems of miscommunication. The aim of the ESSENCE network is to translate these abilities of natural communicating systems to computational systems in order to improve their resilience and robustness, and by doing so to also make these systems more comprehensible to human users. To this end, we will bring together research on phenomena observed in human communication with research from areas that investigate heterogeneous computational communicating systems.

Smart Society

Society is progressively moving towards a socio-technical ecosystem in which the physical and virtual dimensions of life are more and more intertwined and where people interaction, more often than not, takes place with or is mediated by machines. Our goal is to move towards hybrid systems where people and machines tightly work together to build a smarter society. We envision a new generation of Collective Adaptive Systems where humans and machines synergically complement each other and operate collectively to achieve their, possibly conflicting, goals, but which also exhibit an emergent behaviour that is in line with their designers’ objectives.

Vagueness (since 2009)

Ewan Klein, Michael Rovatsos

In this project, we are interested in the practical benefits of using vague terms in multiagent communication. We are currently developing a simulation testbed within which we can experiment with different vague semantics in multiagent communication in a simple application domain, and hope that this will shed more light on the impact of vagueness on the adaptability, robustness, and scalability of evolving semantics.

Planning games (since 2009)

Matt Crosby, Michael Rovatsos

This project looks at multiagent planning domains with self-interested agents. In particular, a parcel delivery gridworld domain is implemented. This domain is highly coupled in terms of the possible interactions between agents and contains interesting scenarios for cooperation. Game Theoretic concepts are applied to develop algorithms for finding stable solutions (joint plans).

Automated norm synthesis (since 2007)

George Christelis, Michael Rovatsos, Ron Petrick

In multiagent systems it is often desirable to achieve coordination through the use of restrictions on agent behaviour. These restrictions, or social norms, conditionally prohibit agent action so as to achieve a social objective. In this project, we are interested in algorithmic processes that can be used to synthesise these restrictions. Our approach adopts a planning-based domain formalism to synthesise norms, and utilises planning itself to investigate what effects the synthesised norms have on the goals of the agents.

Argumentation in planning (since 2007)

Alexandros-Sotiris Belesiotis, Iyad Rahwan, Guillermo Simari, Michael Rovatsos

Autonomous agents transcend their individual capabilities by cooperating towards achieving shared goals. In complex multiagent environments, agents may have different viewpoints due to locality of sensing, different fundamental assumptions about the domain, or simply because different agents may have conducted different inferences and therefore their beliefs may not be aligned. In this project we aim to develp an argumentation-based dialogue framework that allows agents to discuss candidate plans, align their viewpoints and reach agreements.

Modelling learning opponents in games (since 2007)

Francesco Figari, Michael Rovatsos, Ed Hopkins

description to be added

Expectation-strategy-behaviour architecture (since 2006)

Iain Wallace, Michael Rovatsos

Reasoning about others, as performed by agents in order to coordinate their behaviours with those of others, commonly involves forming and updating beliefs about hidden system properties such as other agents’ mental states. The Expectation-Strategy-Behaviour (ESB) framework provides a generic machinery for such practical social reasoning and can be easily coupled with deliberative, knowledge-based architectures such as BDI. The principles of ESB can be used to implement bounded “social” rationality in multiagent designs.

Communication in reinforcement learning (since 2005)

Matthew Whitaker, Alexandros-Sotiris Belesiotis, Jad Hamza, Michael Rovatsos

In this project we are interested in two aspects of how communication can be used in multiagent reinforcement learning: (1) as potentially unreliable advice from an information source that makes suggestions to the agents as to how they could better cooperate; and (2) as signals exchanged by the learners while learning, either for the purposes of communicating part of their own state to overcome partial observability, or to communicate their intended actions.

Collaborative learning (2005-2008)

Jan Tozicka, Xavier Rafael Palou, Michael Rovatsos, Michael Pechoucek

This work resulted in an abstract framework for collaborative agent-based machine learning that allows for the integration of heterogeneous agent learning algorithms and enables knowledge sharing among learners in the form of data and hypothesis sharing (Tozicka et 2008). The advantage of our architecture is that it provides a broader range of potential interactions between collaborating learners than previous approaches. The framework has been successfully applied to different real-world learning problems such as brain tumor classification and vessel tracking.

Empirical semantics (2003-2006)

Matthias Nickles, Michael Rovatsos, Gerhard Weiss, Wilfried Brauer

The aim of this project was to give an alternative characterisation for the semantics of agent communication that was based on expectations based on experience rather than on mental models of other agents or on publicly visible commitments. We developed a probabilistic framework that included both system-level representations of the evolving meaning of expectation-based semantics, and agent-level simplified representations of meaning that can be used for making actual communication decisions from the perspective of an individual agent. A summary of this work can be found in (Nickles et al 2007).

Dynamic semantics (2006-2007)

Michael Rovatsos

Building on the empirical semantics framework, we developed a logic-based mechanism for tracking concrete plan-based semantics of speech acts in a commitment-based agent communication setting. The contribution of this work is that it allows for an explicit representation of different "states" of the meaning of certain utterances where transitions between different states are contingent on agent behaviour. The model is described in (Rovatsos 2007).

Learning dialogue strategies (2000-2005)

Felix Fischer, Michael Rovatsos, Iyad Rahwan, Liz Sonenberg, Gerhard Weiss

In this project, we applied hierarchical reinforcement learning techniques to symbolic agent communication languages to enable agents to learn time-extended policies in a strategic communication environment. (Fischer et al 2005) and (Fischer and Rovatsos 2005) are the main references for this work. Later, we also applied this framework to argumentation-based negotiation (Rovatsos et al 2005); to our knowledge, this was the first work to attempt online learning of argumentation strategies in multiagent dialogues.

Interaction frames and framing architecture (2000-2004)

Michael Rovatsos, Kai Paetow, Felix Fischer, Gerhard Weiss

The aim of this project was to design an architecture for managing strategic interactions between agents based on concepts of "frames" and "framing" as suggested by the sociologist Erving Goffman. The resulting framework provided a holistic method for reasoning about agent-to-agent communicative interactions and for learning how to abstract from individual interaction experiences and to optimise interaction choices in the long-term. An overview of the framework is given in (Rovatsos et al 2002)

Autonomy modelling (2001-2004)

Gerhard Weiss, Matthias Nickles, Michael Rovatsos, Christian Meindl

This work developed languages and theoretical models for describing autonomy relationships between interacting agents and how these change with communication. We developed both a conceptual framework that allows for viewing autonomy as a communication-mediated variable property of social systems, and concrete formal languages that allow for the specification of deontic relationships and how these change over time. See (Rovatsos and Weiss 2005) and (Weiss et al 2005).

Expectation-oriented analysis and design (2000-2004)

Matthias Nickles, Michael Rovatsos, Gerhard Weiss, Wilfried Brauer

The goal of this project was to develop a software engineering methodology based on modelling the evolution of expectations among interacting agents in agent-based systems. In contrast to the more theoretical work on empirical semantics, here we suggested a concrete set of guidelines for representing, tracking and improving systems of changing expectations as a suitable method for engineering open systems in which it is hard to predict agent behaviour at design time. The results of this work are discussed in (Nickles et al 2005).

Opponent classification (2000-2007)

Marco Wolf, Brian Collins, Michael Rovatsos, Gerhard Weiss

This project was concerned with learning how to dynamically "stereotype" opponents in games with many opponents into different classes based on their strategies. We developed the AdHoc heuristic that was later on used by other researchers and applied to such domains as robotic soccer. Relevant publications are (Rovatsos and Wolf 2002) and (Rovatsos et al 2003). We also developed methods for improving player satisfaction in video games based on classifying human opponents according to their level of skill at the game and adapting to this level (Collins and Rovatsos, 2006).

Layered learning (1999-2000)

Michael Rovatsos, Juergen Lind

In this work we developed a layered learning architecture capable of learning to play repeated games with large action spaces and greater numbers of players than in many other game-theoretic studies. The architecture consisted of a neural layer that would learn the utility function of the game, a genetic algorithm that would attempt to approximate the other's best-response strategies, and a layer using Probabilistic Ordering Models (a technique proposed for the architecture) that tries to model opponents' preferences. See (Rovatsos and Lind 2000) for a summery of the main results.

Trust and reputation (since 1999)

Michael Schillo, Michael Rovatsos, Petra Funk, Sebastian Mhatre, Mariola Mier

Early work on this topic was concerned with integrating witness information into models of multiagent trust, and was the first model to suggest the use of such information. The model is described in one of the most-cited early papers on trust and reputation (Schillo et al 2000) Later work looked at estimating the strategic value of lying in repeated games, and currently we are interested in hierarchical notions of trust (e.g. intra- vs inter-group trust).

Agents Group


edit SideBar

Blix theme adapted by David Gilbert, powered by PmWiki