Learning and Reasoning in Social Contexts (WP6)

Partners

IST, CNR, UNIROMA1, BIU, CNRS, UOXF, VUB, CEA, UArtois, TU Delft, DFKI, EPFL, CSIC, NKUA, CINI, slovak.AI, TNO, UGA, UPV, ENG

See partner page for details on participating organisations.

People

WP leader: Ana Paiva (IST-UL)

BAR ILAN UNIVERSITY (BIU): Sarit Kraus (BIU)

CONSIGLIO NAZIONALE DELLE RICERCHE (CNR): Amadeo Cesta, Vito Trianni, Stefano Borgo, Andrea Orlandini, Sara Colantonio, Flavio Lombardi

DEUTSCHES FORSCHUNGSZENTRUM FUR KUNSTLICHE INTELLIGENZ GMBH (DFKI): Philipp Slusallek, Matthias Klusch, André Antakli, Elena Jaramillo, André Meyer-Vitali

ÉCOLE POLYTECHNIQUE FÉDÉRALE DE LAUSANNE (EPFL): Boi Faltings, Panayiotis Danassis, Zeki Erden

INSTITUTO DE INVESTIGACIÓN EN INTELIGENCIA ARTIFICIAL – CONSEJO SUPERIOR DE INVESTIGACIONES CIENTÍFICAS (IIA-CSIC): Carles Sierra, Nieves Montes, Athina Georgara

INSTITUTO SUPERIOR TÉCNICO – UNIVERSIDADE DE LISBOA (IST-UL): Ana Paiva (WP leader), Alberto Sardinha, Francisco Santos, Maria José Ferreira, Henrique Fonseca

TECHNISCHE UNIVERSITEIT DELFT (TUD): Catholijn Jonker, Aaron Ding, Amineh Ghorbani, Pradeep Murukannaiah, Frans Oliehoek, Luciano Siebert, Wiebke Toussaint, Neil Yorke-Smith, Arkady Zgonnikov

NEDERLANDSE ORGANISATIE VOOR TOEGEPAST NATUURWETENSCHAPPELIJK ONDERZOEK (TNO): Wico Mulder

UNIVERSITE GRENOBLE ALPES (UGA): Jérôme Euzenat, Manuel Atencia Arcas, Line Van den berg, Andrea Kalaitzakis, Alban Flandrin

UNIVERSITY OF OXFORD (UOx): Michael Wooldridge, Anisoara Calinescu, Thomas Lukasiewicz

UNIVERSITAT POLITECNICA DE VALENCIA (UPV): Vicent Botti, Vicente Julián, Estefania Argente, Miguel Rebollo, Emilio Vivancos, José María Sempere, Joaquín Taverner, Stella Heras, Soledad Valero

VRIJE UNIVERSITEIT BRUSSEL (VUB): Ann Nowé, Tom Lenaerts, Elias Fernández Domingos, Eladio Montero, Inês Terrucha, Axel Abels, Yannick Molinghen, Jelena Grujic, Diederik Roijers, Raphael Avalos, Mahmoud Elbarbari

SLOVAK AI: Michal Kompan, Maria Bielikova, Igor Farkas

About WP6

This theme focuses on the fundamental question: How do AI agents act and learn in a society?

Agents should not reason, learn and act in isolation. They will need to do it with others and among others. So, this theme will explore the foundations of how AI systems should communicate, collaborate, negotiate and reach agreements with other AI and (eventually) human agents within a multi-agent system (MAS). We will go from intelligence centred in one agent to social intelligence and social behaviours, laying down the foundation that leads to the understanding and engineering of hybrid societies composed of AI and humans. Nowadays computation is increasingly distributed and the IoT will enable devices to become more intelligent, to communicate, and in the end to socialise. Social AI will be observable within Massive Multi-Agent Systems (MMAS), which will include all sorts of devices and different interaction modes with people, organisations and institutions. This theme will explore the current AI techniques to bring the social component into the foundations of AI.

The main questions that will drive the research on the fundamentals of social AI are:

  • How do we empower individual AI agents to communicate with each other, collaborate, negotiate and reach agreements? How can agents coordinate to fairly share common resources?
  • How can we make agents learn from each other in a responsible and fair way, leading to more intelligent behavior?
  • How to create trustworthy hybrid human-AI societies that fulfil humans’ expectations and follow their requirements?”

WP6 Tasks

Task 6.1: Modelling social cognition, collaboration and teamwork (Task Lead: IIIA-CSIC)

To study the modelling of agent’s cognitive capabilities that integrate individual knowledge and behaviour (possibly arising from model-free approaches) with knowledge available to and from other agents (possibly obtained at different times and from different perspectives). This also includes studying the foundations, techniques, algorithms and tools for designing social AI systems. To achieve that, agents should have the capability of understanding others, reason about them (for example have Theory of Mind) and be able to act in a team. We will investigate novel algorithms to perform on-line team formation. Such algorithms will allow to dynamically assemble teams of agents (and possibly humans) to complete tasks that are requested to be serviced along time. We will also consider aspects such as: fostering diversity within teams in terms of cognitive abilities, personality and gender and manage the dynamics of teams. We will also cater for agents’ motivations by considering their preferences about taking part in tasks as well as how they perceive others, namely their potential team-mates. Finally, our algorithms will also cater to the perception and past observations of assessing agents about teams. Therefore, besides being capable of on-line operation, an important novelty of our team formation algorithm will stem from considering the modelling of the perceptions about others of both working agents and assessing agents, namely from considering social cognition aspects.

Task 6.2: Theoretical models for cooperation between agents (Task Lead: UOX)

In this task we will use economic paradigms to study and advance the foundations, techniques, algorithms and tools for collaborative decision making by social agents. As AI agents act on behalf of people, a first crucial issue is to model and elicit their preferences and in particular to aggregate and mediate preferences of multiple stakeholders in a fair manner. The second issue is that self-interested agents often need to be given additional incentives to motivate them to execute their tasks faithfully. While economics has shown many impossibility results, multi-agent systems often allow creating artificial settings that allow more powerful mechanisms. In particular, machine learning allows tailoring mechanisms to the particular preferences of agents, using a technique called automated mechanism design. Another opportunity arises from the fact that most AI optimization algorithms now use randomization which invalidates many impossibility results from economics, allowing for example truthful protocols for social choice and budget-balanced truthful auctions.

Task 6.3: Learning from others (Task Lead: VUB)

We will study the foundations, techniques, algorithms and tools for social learning. We will address the key question of who should learn from whom, and what should be learned. The setting of a single learning agent guided by another agents or by humans has been extensively studied in the past few years. It can exhibit different forms such as learning from demonstrations, advice and imitation learning. Through shaping and interaction, learning can be guided, and when the shaping obeys certain conditions, such a potential function, the learning can still be guaranteed to converge to an optimal behavior. When the learning agent needs to perform a task which is not the same as the ‘teacher’ agent, or when the capabilities of the learning agent or different, one might use transfer learning approaches. In this task we will investigate the research questions arising from placing multiple learning agents in a social context with other agents. How can these agents be efficiently guided in their joint learning process? And how to explore the link between representation, optimization and learning in a multi-agent learning setting. We will also consider federated learning, where agents collaborate to learn a joint model while keeping their individual data private.

Task 6.4: Emergent Behaviour, agent societies and social networks (Task Lead: CNR)

In this task we will look at the society level, studying the foundations, techniques, algorithms and tools for modeling and designing complex social structures, organizations and institutions. AI has already influenced the work in socio-technical systems (STS), in cyber-physical systems (CPS) and in multi-agent systems (MAS), that is, the most successful approaches for understanding, controlling and maintaining systems where large populations of natural and artificial entities interact in multiple ways with rich information exchanges and mutual behavioural dependencies. Some of the different approaches to modelling social systems that we will consider in TAILOR are self-organization, evolutionary game theoretical paradigms and agent-based simulations. We will also consider normative systems that arise from the collaborative agreements of the members of the society on the norms that regulate their interactions.

Task 6.5: Synergies Industry, Challenges, Roadmap on social AI system (Task leader: TNO)

Task 6.6: Fostering the AI scientific community on the theme of social AI (Task leader: IST-UL)

This task aims at promoting activities such as bilateral/multilateral meetings among scientists nad student visits, organising workshops on Social AI, promoting the area, organising summer schools, TAILOR conference and other common activities related to the area of Social AI.

News related to WP6

  • Ana Paiva elected in the AAAI 2023 Fellow Class

    The Association for the Advancement of Artificial Intelligence (AAAI) established the Fellows program in 1990 to acknowledge individuals who have made significant and prolonged contributions to the field of AI, typically spanning at least ten years. Each February, AAAI members nominate individuals they believe have achieved extraordinary distinction in AI. Then, a committee of nine…

    Read full text

  • 6 TAILOR scientists in new EurAI board

    TAILOR scientists Giuseppe de Giacomo, Fredrik Heintz, Holger Hoos, Ana Paiva, Carles Sierra and Manolis Koubarakis were recently elected Member of the EurAI Board.

    Read full text

  • Impressions from TAILOR Conference in Prague

    On 13th and 14th of September, TAILOR had its second annual conference. This time the conference was hosted in Prague, at the beautiful location of Charles University. The major objectives of the conference was to discuss about what TAILOR did so far, to make a plan for the next year, and finally to meet in…

    Read full text

  • Keynotes from TAILOR scientists at IJCAI-ECAI 2022 in Vienna

    IJCAI-ECAI22 is coming up and TAILOR will be there! The conference will be in Vienna, from 23rd to 29th of July, 2022. Two keynotes will be given by TAILOR scientists:  Gerhard Widmer (JKU Linz) will talk about “AI & Music: On the Role of AI in Studying a Human Art Form” on Monday 23rd, at 18.00…

    Read full text