In recent years, computational improvements have allowed for more nuanced, data-driven and geographically explicit agent-based simulations. Yet, simulations have struggled to adequately represent the attributes that motivate and drive agents’ actions. Existing population synthesis frameworks usually generate agent profiles limited to socio-demographic attributes. In this paper, we introduce a novel population synthesis framework that integrates a motivational layer into the traditional individual and house-hold socio-demographic layers. Our research extends the profile of agents in synthetic populations to incorporate data on values, ideologies, opinions and vital priorities, all of which play a key role in motivating agents’ behaviour. This motivational layer paves the way for developing data-driven decision-making mechanisms in future agent-based simulations. Our methodology combines microdata and macrodata within different Bayesian network structures or models. This method allows to generate synthetic populations that integrate motivational information while preserving the inherent socio-demographic distributions of the real population.

The global rise in homelessness calls for urgent and alternative policy solutions. Non-profits and governmental organizations alert about the many challenges faced by people experiencing homelessness (PEH), which include not only the lack of shelter but also the lack of opportunities for personal development. In this context, the capability approach (CA), which underpins the United Nations Sustainable Development Goals (SDGs), provides a comprehensive framework to assess inequity in terms of real opportunities. This paper explores how the CA can be combined with agent-based modelling and reinforcement learning. The goals are: (1) implementing the CA as a Markov Decision Process (MDP), (2) building on such MDP to develop a rich decision-making model that accounts for more complex motivators of behaviour, such as values and needs, and (3) developing an agent-based simulation framework that allows to assess alternative policies aiming to expand or restore people's capabilities. The framework is developed in a real case study of health inequity and homelessness, working in collaboration with stakeholders, non-profits and domain experts. The ultimate goal of the project is to develop a novel agent-based simulation framework, rooted in the CA, which can be replicated in a diversity of social challenges to assess policies in a non-invasive way.

Using norms to guide and coordinate interactions has gained tremendous attention in the multi-agent community. However, new challenges arise as the interest moves towards dynamic socio-technical systems, where human and software agents interact, and interactions are required to adapt to human's changing needs. For instance, different agents (human or software) might not have the same understanding of what it means to violate a norm (e.g., what characterizes hate speech), or their understanding of a norm might change over time (e.g., what constitutes an acceptable response time). The challenge is to address these issues by learning the meaning of a norm violation from limited interaction data. For this, we use batch and incremental learning to train an ensemble of classifiers. Ensemble learning and data-sampling handle the imbalanced class distribution of the interaction stream. At the same time, the training approaches use different strategies to ensure that the ensemble models reflect the latest community view on the meaning of norm violation. Batch learning uses weight assignment, while incremental learning continuously updates the ensemble models as community members interact. Here, we extend our previous work by creating a different balance strategy for online learning and integrating interpretability to understand norm violations. Additionally, we evaluate the proposed approaches in the context of Wikipedia article edits, where interactions revolve around editing articles, and the norm in question is prohibiting vandalism. Lastly, we conduct ablation studies to compare the ensemble's performance against a single model approach and to examine the behavior of two data sampling techniques. Results indicate that the different machine learning frameworks can learn the meaning of a norm violation in a setting with data imbalance and concept drift, although with significant differences.

Ostrom's Institutional Analysis and Development (IAD) framework represents a comprehensive theoretical effort to identify and outline the variables that determine the outcome in any social interaction. Taking inspiration from it, we define the Action Situation Language (ASL), a machine-readable logical language to express the components of a multiagent interaction, with a special focus on the rules adopted by the community. The ASL is complemented by a game engine that takes an interaction description as input and automatically grounds its semantics as an Extensive-Form Game (EFG), which can be readily analysed using standard game-theoretical solution concepts. Overall, our model allows a community of agents to perform what-if analysis on a set of rules being considered for adoption, by automatically connecting rule configurations to the outcomes they incentivize.

Cross-community learning incorporates data from different sources to leverage task-specific solutions in a target community. This approach is particularly interesting for low-resource or newly created online communities, where data formalizing interactions between agents (community members) are limited. In such scenarios, a normative system that intends to regulate online interactions faces the challenge of continuously learning the meaning of norm violation as communities' views evolve, either with changes in the understanding of what it means to violate a norm or with the emergence of new violation classes. To address this issue, we propose the Cross-community Adapter Learning (CAL) framework, which combines adapters and transformer-based models to learn the meaning of norm violations expressed as textual sentences. Additionally, we analyze the differences in the meaning of norm violations between communities, using Integrated Gradients (IG) to understand the inner workings of our model and calculate a global relevance score that indicates the relevance of words for violation detection. Results show that cross-community learning enhances CAL's performance while explaining the differences in the meaning of norm-violating behavior based on community members' feedback. We evaluate our proposal in a small set of interaction data from Wikipedia, in which the norm prohibits hate speech.

Abstract This paper presents a novel model, called TomAbd, that endows autonomous agents with Theory of Mind capabilities. TomAbd agents are able to simulate the perspective of the world that their peers have and reason from their perspective. Furthermore, TomAbd agents can reason from the perspective of others down to an arbitrary level of recursion, using Theory of Mind of $$n^{\text {th}}$$ n th order. By combining the previous capability with abductive reasoning, TomAbd agents can infer the beliefs that others were relying upon to select their actions, hence putting them in a more informed position when it comes to their own decision-making. We have tested the TomAbd model in the challenging domain of Hanabi, a game characterised by cooperation and imperfect information. Our results show that the abilities granted by the TomAbd model boost the performance of the team along a variety of metrics, including final score, efficiency of communication, and uncertainty reduction.

Abstract Using norms to guide and coordinate interactions has gained tremendous attention in the multiagent community. However, new challenges arise as the interest moves towards dynamic socio-technical systems, where human and software agents interact, and interactions are required to adapt to changing human needs. For instance, different agents (human or software) might not have the same understanding of what it means to violate a norm (e.g., what characterizes hate speech), or their understanding of a norm might change over time (e.g., what constitutes an acceptable response time). The challenge is to address these issues by learning to detect norm violations from the limited interaction data and to explain the reasons for such violations. To do that, we propose a framework that combines Machine Learning (ML) models and incremental learning techniques. Our proposal is equipped to solve tasks in both tabular and text classification scenarios. Incremental learning is used to continuously update the base ML models as interactions unfold, ensemble learning is used to handle the imbalance class distribution of the interaction stream, Pre-trained Language Model (PLM) is used to learn from text sentences, and Integrated Gradients (IG) is the interpretability algorithm. We evaluate the proposed approach in the use case of Wikipedia article edits, where interactions revolve around editing articles, and the norm in question is prohibiting vandalism. Results show that the proposed framework can learn to detect norm violation in a setting with data imbalance and concept drift.

Policies that seek to mitigate poverty by acting on equal opportunity have been found to aggravate discrimination against the poor (aporophobia), since individuals are made responsible for not progressing in the social hierarchy. Only a minority of the poor benefit from meritocracy in this era of growing inequality, generating resentment among those who seek to escape their needy situations by trying to climb up the ladder. Through the formulation and development of an agent-based social simulation, this study aims to analyse the role of norms implementing equal opportunity and social solidarity principles as enhancers or mitigators of aporophobia, as well as the threshold of aporophobia that would facilitate the success of poverty-reduction policies. The ultimate goal of the social simulation is to extract insights that could help inform and guide a new generation of policy making for poverty reduction by acting on the discrimination against the poor, in line with the UN “Leave No One Behind” principle. An “aporophobia-meter” will be developed and guidelines will be drafted based on both the simulation results and a review of poverty reduction policies at regional levels.

The Institutional Analysis and Development (IAD) framework developed by Elinor Ostrom and colleagues provides great conceptual clarity on the immensely varied topic of social interactions. In this work, we propose a computational model to examine the impact that any of the variables outlined in the IAD framework has on the resulting social interactions. Of particular interest are the rules adopted by a community of agents, as they are the variables most susceptible to change in the short term. To provide systematic descriptions of social interactions, we define the Action Situation Language (ASL) and provide a game engine capable of automatically generating formal game-theoretical models out of ASL descriptions. Then, by incorporating any agent decision-making models, the connection from a rule configuration description to the outcomes encouraged by it is complete. Overall, our model enables any community of agents to perform what-if analysis, where they can foresee and examine the impact that a set of regulations will have on the social interaction they are engaging in. Hence, they can decide whether their implementation is desirable.

This paper proposes a shift in how technology is currently being developed by giving people, the users, control over their technology. We argue that users should have a say in the behaviour of the technologies that mediate their online interactions and control their private data. We propose 'partakable technologies', technologies where users can come together to discuss and agree on its features and functionalities. To achieve this, we base our proposal on a number of existing technologies in the fields of agreement technologies, natural language processing, normative systems, and formal verification. As an IJCAI early career spotlight paper, the paper provides an overview of the author's expertise in these different areas.

This paper proposes a computational model based on peer reviews for assessing the reputation of researchers and research work. We argue that by relying on peer opinions, we address some of the pitfalls of current approaches for calculating the reputation of authors and papers. We also introduce a much needed feature for review management: calculating the reputation of reviews and reviewers.

We propose a novel trust model for assessing the trustworthiness of advice. We say an advice is composed of a plan to execute and a goal to be fulfilled. The expectation of an advice's outcome is calculated by assessing the probabilities of commiting to and executing the plan, and the probability of the executed plan fulfiling the intended goal. The probabilities are learned from similar past experiences.

This paper proposes the notion of experience to help situate agents in their environment, providing a link on how the continually evolving environment impacts the evolution of an agent's BDI model and vice versa. Then, using the notion of shared experience as a primitive construct, we develop a novel formal model of shared intention which we believe more adequately describes social behaviour than traditional BDI logics that focus on individual agents. Whilst many philosophers have argued that collective intentionality cannot always be equated to the collection of the individual agents' intentions, there has been no AI model that addresses this issue. We believe this is the first attempt to develop an explicit notion of shared experience from an AI perspective.

This article addresses the problem of finding suitable agents to collaborate with for a given interaction in distributed open systems, such as multiagent and P2P systems. The agent in question is given the chance to describe its confidence in its own capabilities. However, since agents may be malicious, misinformed, suffer from miscommunication, and so on, one also needs to calculate how much trusted is that agent. This article proposes a novel trust model that calculates the expectation about an agent's future performance in a given context by assessing both the agent's willingness and capability through the semantic comparison of the current context in question with the agent's performance in past similar experiences. The proposed mechanism for assessing trust may be applied to any real world application where past commitments are recorded and observations are made that assess these commitments, and the model can then calculate one's trust in another with respect to a future commitment by assessing the other's past performance.

Trust and reputation measures are crucial in distributed open systems where agents need to decide whom or what to choose. Existing work has overlooked the impact of an entity's position in its structural graph and its effect on the propagation of trust in such graphs. This paper presents an algorithm for the propagation of reputation in structural graphs. It allows agents to infer their opinion about unfamiliar entities based on their view of related entities. The proposed mechanism focuses on the “part of” relation to illustrate how reputation may flow (or propagate) from one entity to another. The paper bases its reputation measures on opinions, which it defines as probability distributions over an evaluation space, providing a rich representation of opinions.