Author name cluster

Marc Serramia

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

AAMAS Conference 2024 Conference Paper

Multi-user Norm Consensus

Marc Serramia
Natalia Criado
Michael Luck

Many agents act in environments with multiple human users, from care robots to smart assistants. When interacting in multi-user environments it is paramount that these agents act as all users expect. However, it is not always possible to have well-defined collective preferences, nor to easily infer them from individual preferences. This is especially true in fast changing environments, like a device placed in a public space where users can enter and exit freely. In response, this paper proposes a model to represent individual preferences about the behaviour of an agent and a mechanism to find multi-user consensuses over these preferences. Norms can then be generated to ensure that when the agent follows them it will act according to the preferences of all users. We formalise what a consensus norm is and what properties the set of consensus norms should satisfy (i. e. generate the minimum number of norms while maximising the coverage of user preferences). We provide an optimisation approach to find this set of norms and show that our approach satisfies the aforementioned properties.

PDF

AAMAS Conference 2024 Conference Paper

Value Alignment in Participatory Budgeting

Marc Serramia
Maite Lopez-Sanchez
Juan A. Rodriguez-Aguilar
Stefano Moretti

Participatory budgeting empowers citizens to take an active role in shaping their government’s policies by influencing the allocation of a limited budget. In this process, citizens file various proposals and then collectively decide which ones should receive funding through a voting system. While participatory budgets have garnered significant attention in research and practice, one aspect so far overlooked is the ethical dimension of the proposals. Thus, beyond just gauging citizen preferences, we propose also to consider how these initiatives align with the government’s core values. Specifically, we apply optimisation techniques to solve a multi-criteria decision problem that considers both citizen support and value alignment when choosing the proposals to fund. We illustrate our method in two real case studies and analyse how we can combine both criteria in an egalitarian way that does not necessarily compromise the will of citizens and may encourage governments to broaden the objectives and increase the allocated budget.

PDF

AAMAS Conference 2023 Conference Paper

Predicting Privacy Preferences for Smart Devices as Norms

Marc Serramia
William Seymour
Natalia Criado
Michael Luck

Smart devices, such as smart speakers, are becoming ubiquitous, and users expect these devices to act in accordance with their preferences. In particular, since these devices gather and manage personal data, users expect them to adhere to their privacy preferences. However, the current approach of gathering these preferences consists in asking the users directly, which usually triggers automatic responses failing to capture their true preferences. In response, in this paper we present a collaborative filtering approach to predict user preferences as norms. These preference predictions can be readily adopted or can serve to assist users in determining their own preferences. Using a dataset of privacy preferences of smart assistant users, we test the accuracy of our predictions.

PDF

AAMAS Conference 2022 Conference Paper

Towards Pluralistic Value Alignment: Aggregating Value Systems Through l p -Regression

Roger Lera-Leri
Filippo Bistaffa
Marc Serramia
Maite Lopez-Sanchez
Juan Rodriguez-Aguilar

Dealing with the challenges of an interconnected globalised world requires to handle plurality. This is no exception when considering value-aligned intelligent systems, since the values to align with should capture this plurality. So far, most literature on valuealignment has just considered a single value system. Thus, this paper advances the state of the art by proposing a method for the aggregation of value systems. By exploiting recent results in the social choice literature, we formalise our aggregation problem as an optimisation problem. We then cast such problem as an ℓ𝑝-regression problem. By doing so, we provide a general theoretical framework to model and solve the above-mentioned problem. Our aggregation method allows us to consider a range of ethical principles, from utilitarian (maximum utility) to egalitarian (maximum fairness). We illustrate the aggregation of value systems by considering realworld data from the European Values Study and we show how different consensus value systems can be obtained depending on the ethical principle of choice.

PDF

JAAMAS Journal 2021 Journal Article

On the dominant set selection problem and its application to value alignment

Marc Serramia
Maite López-sánchez
Juan Antonio Rodríguez-Aguilar

Abstract Decision makers can often be confronted with the need to select a subset of objects from a set of candidate objects by just counting on preferences regarding the objects’ features. Here we formalise this problem as the dominant set selection problem. Solving this problem amounts to finding the preferences over all possible sets of objects. We accomplish so by: (i) grounding the preferences over features to preferences over the objects themselves; and (ii) lifting these preferences to preferences over all possible sets of objects. This is achieved by combining lex-cel –a method from the literature—with our novel anti-lex-cel method, which we formally (and thoroughly) study. Furthermore, we provide a binary integer program encoding to solve the problem. Finally, we illustrate our overall approach by applying it to the selection of value-aligned norm systems.

Details DOI

AAMAS Conference 2018 Conference Paper

Moral Values in Norm Decision Making

Marc Serramia
Maite Lopez-Sanchez
Juan A. Rodriguez-Aguilar
Manel Rodriguez
Michael Wooldridge
Javier Morales
Carlos Ansotegui

Most often, both agents and human societies use norms to coordinate their on-going activities. Nevertheless, choosing the ‘right’ set of norms to regulate these societies constitutes an open problem. Firstly, intrinsic norm relationships may lead to inconsistencies in the chosen set of norms. Secondly, and more importantly, there is an increasing demand of including ethical considerations in the decision making process. This paper focuses on choosing the ‘right’ norms by considering moral values together with society’s partial preferences over these values and the extent to which candidate norms promote them. The resulting decision making problem can then be encoded as a linear program, and hence solved by state-ofthe art solvers. Furthermore, we empirically test several optimisation scenarios so to determine the system’s performance and the characteristics of the problem that affect its hardness.

PDF

AAMAS Conference 2017 Conference Paper

Automating Decision Making to Help Establish Norm-Based Regulations

Maite Lopez-Sanchez
Marc Serramia
Juan A. Rodriguez-Aguilar
Javier Morales
Michael Wooldridge

Norms have been extensively proposed as coordination mechanisms for both agent and human societies. Nevertheless, choosing the norms to regulate a society is by no means straightforward. The reasons are twofold. First, the norms to choose from may not be independent (i. e, they can be related to each other). Second, different preference criteria may be applied when choosing the norms to enact. On the one hand, this paper considers norm representation power and cost as alternative preference criteria. On the other hand, it identifies three different norm relationships –namely, generalisation, exclusivity, and substitutability. We show that the decisionmaking problem faced by policy makers can be encoded as a linear program, and hence solved with the aid of state-of-the-art solvers.

PDF