arXiv subjects

Tom Lenaerts

Publications and source records attributed to Tom Lenaerts.

34 records · Page 2Linked to original sources

arXiv2023

Expertise Trees Resolve Knowledge Limitations in Collective Decision-Making

Experts advising decision-makers are likely to display expertise which varies as a function of the problem instance. In practice, this may lead to sub-optimal or discriminatory decisions against minority cases. In this work we model such changes in depth and breadth of knowledge as a partitioning of the problem space into regions of differing expertise. We provide here new algorithms that explicitly consider and adapt to the relationship between problem instances and experts' knowledge. We first propose and highlight the drawbacks of a naive approach based on nearest neighbor queries. To address these drawbacks we then introduce a novel algorithm - expertise trees - that constructs decision trees enabling the learner to select appropriate models. We provide theoretical insights and empirically validate the improved performance of our novel approach on a range of problems for which existing methods proved to be inadequate.

cs.AI↗

arXiv2023

ACROCPoLis: A Descriptive Framework for Making Sense of Fairness

Fairness is central to the ethical and responsible development and use of AI systems, with a large number of frameworks and formal notions of algorithmic fairness being available. However, many of the fairness solutions proposed revolve around technical considerations and not the needs of and consequences for the most impacted communities. We therefore want to take the focus away from definitions and allow for the inclusion of societal and relational aspects to represent how the effects of AI systems impact and are experienced by individuals and social groups. In this paper, we do this by means of proposing the ACROCPoLis framework to represent allocation processes with a modeling emphasis on fairness aspects. The framework provides a shared vocabulary in which the factors relevant to fairness assessments for different situations and procedures are made explicit, as well as their interrelationships. This enables us to compare analogous situations, to highlight the differences in dissimilar situations, and to capture differing interpretations of the same situation by different stakeholders.

cs.CY↗

arXiv2022

Dealing with Expert Bias in Collective Decision-Making

Quite some real-world problems can be formulated as decision-making problems wherein one must repeatedly make an appropriate choice from a set of alternatives. Multiple expert judgements, whether human or artificial, can help in taking correct decisions, especially when exploration of alternative solutions is costly. As expert opinions might deviate, the problem of finding the right alternative can be approached as a collective decision making problem (CDM) via aggregation of independent judgements. Current state-of-the-art approaches focus on efficiently finding the optimal expert, and thus perform poorly if all experts are not qualified or if they are overly biased, thereby potentially derailing the decision-making process. In this paper, we propose a new algorithmic approach based on contextual multi-armed bandit problems (CMAB) to identify and counteract such biased expertise. We explore homogeneous, heterogeneous and polarised expert groups and show that this approach is able to effectively exploit the collective expertise, outperforming state-of-the-art methods, especially when the quality of the provided expertise degrades. Our novel CMAB-inspired approach achieves a higher final performance and does so while converging more rapidly than previous adaptive algorithms.

cs.AI↗

arXiv2022

The art of compensation: how hybrid teams solve collective risk dilemmas

It is widely known how the human ability to cooperate has influenced the thriving of our species. However, as we move towards a hybrid human-machine future, it is still unclear how the introduction of AI agents in our social interactions will affect this cooperative capacity. Within the context of the one-shot collective risk dilemma, where enough members of a group must cooperate in order to avoid a collective disaster, we study the evolutionary dynamics of cooperation in a hybrid population made of both adaptive and fixed-behavior agents. Specifically, we show how the first learn to adapt their behavior to compensate for the behavior of the latter. The less the (artificially) fixed agents cooperate, the more the adaptive population is motivated to cooperate, and vice-versa, especially when the risk is higher. By pinpointing how adaptive agents avoid their share of costly cooperation if the fixed-behavior agents implement a cooperative policy, our work hints towards an unbalanced hybrid world. On one hand, this means that introducing cooperative AI agents within our society might unburden human efforts. Nevertheless, it is important to note that costless artificial cooperation might not be realistic, and more than deploying AI systems that carry the cooperative effort, we must focus on mechanisms that nudge shared cooperation among all members in the hybrid system.

cs.CY↗

arXiv2022

Inferring Strategies from Observations in Long Iterated Prisoner's Dilemma Experiments

While many theoretical studies have revealed the strategies that could lead to and maintain cooperation in the Iterated Prisoner's Dilemma, less is known about what human participants actually do in this game and how strategies change when being confronted with anonymous partners in each round. Previous attempts used short experiments, made different assumptions of possible strategies, and led to very different conclusions. We present here two long treatments that differ in the partner matching strategy used, i.e. fixed or shuffled partners. Here we use unsupervised methods to cluster the players based on their actions and then Hidden Markov Model to infer what are those strategies in each cluster. Analysis of the inferred strategies reveals that fixed partner interaction leads to a behavioral self-organization. Shuffled partners generate subgroups of strategies that remain entangled, apparently blocking the self-selection process that leads to fully cooperating participants in the fixed partner treatment. Analyzing the latter in more detail shows that AllC, AllD, TFT- and WSLS-like behavior can be observed. This study also reveals that long treatments are needed as experiments less than 25 rounds capture mostly the learning phase participants go through in these kinds of experiments.

cs.GT↗

arXiv2022

Artificial Intelligence Development Races in Heterogeneous Settings

Regulation of advanced technologies such as Artificial Intelligence (AI) has become increasingly important, given the associated risks and apparent ethical issues. With the great benefits promised from being able to first supply such technologies, safety precautions and societal consequences might be ignored or shortchanged in exchange for speeding up the development, therefore engendering a racing narrative among the developers. Starting from a game-theoretical model describing an idealised technology race in a fully connected world of players, here we investigate how different interaction structures among race participants can alter collective choices and requirements for regulatory actions. Our findings indicate that, when participants portray a strong diversity in terms of connections and peer-influence (e.g., when scale-free networks shape interactions among parties), the conflicts that exist in homogeneous settings are significantly reduced, thereby lessening the need for regulatory actions. Furthermore, our results suggest that technology governance and regulation may profit from the world's patent heterogeneity and inequality among firms and nations, so as to enable the design and implementation of meticulous interventions on a minority of participants, which is capable of influencing an entire population towards an ethical and sustainable use of advanced technologies.

cs.AI↗

arXiv2021

Voluntary safety commitments provide an escape from over-regulation in AI development

With the introduction of Artificial Intelligence (AI) and related technologies in our daily lives, fear and anxiety about their misuse as well as the hidden biases in their creation have led to a demand for regulation to address such issues. Yet blindly regulating an innovation process that is not well understood, may stifle this process and reduce benefits that society may gain from the generated technology, even under the best intentions. In this paper, starting from a baseline model that captures the fundamental dynamics of a race for domain supremacy using AI technology, we demonstrate how socially unwanted outcomes may be produced when sanctioning is applied unconditionally to risk-taking, i.e. potentially unsafe, behaviours. As an alternative to resolve the detrimental effect of over-regulation, we propose a voluntary commitment approach wherein technologists have the freedom of choice between independently pursuing their course of actions or establishing binding agreements to act safely, with sanctioning of those that do not abide to what they pledged. Overall, this work reveals for the first time how voluntary commitments, with sanctions either by peers or an institution, leads to socially beneficial outcomes in all scenarios envisageable in a short-term race towards domain supremacy through AI technology. These results are directly relevant for the design of governance and regulatory policies that aim to ensure an ethical and responsible AI technology development process.

cs.AI↗

arXiv2021

Delegation to autonomous agents promotes cooperation in collective-risk dilemmas

Home assistant chat-bots, self-driving cars, drones or automated negotiations are some of the several examples of autonomous (artificial) agents that have pervaded our society. These agents enable the automation of multiple tasks, saving time and (human) effort. However, their presence in social settings raises the need for a better understanding of their effect on social interactions and how they may be used to enhance cooperation towards the public good, instead of hindering it. To this end, we present an experimental study of human delegation to autonomous agents and hybrid human-agent interactions centered on a public goods dilemma shaped by a collective risk. Our aim to understand experimentally whether the presence of autonomous agents has a positive or negative impact on social behaviour, fairness and cooperation in such a dilemma. Our results show that cooperation increases when participants delegate their actions to an artificial agent that plays on their behalf. Yet, this positive effect is reduced when humans interact in hybrid human-agent groups. Finally, we show that humans are biased towards agent behaviour, assuming that they will contribute less to the collective effort.

cs.HC↗

arXiv2020

Mediating Artificial Intelligence Developments through Negative and Positive Incentives

The field of Artificial Intelligence (AI) is going through a period of great expectations, introducing a certain level of anxiety in research, business and also policy. This anxiety is further energised by an AI race narrative that makes people believe they might be missing out. Whether real or not, a belief in this narrative may be detrimental as some stake-holders will feel obliged to cut corners on safety precautions, or ignore societal consequences just to "win". Starting from a baseline model that describes a broad class of technology races where winners draw a significant benefit compared to others (such as AI advances, patent race, pharmaceutical technologies), we investigate here how positive (rewards) and negative (punishments) incentives may beneficially influence the outcomes. We uncover conditions in which punishment is either capable of reducing the development speed of unsafe participants or has the capacity to reduce innovation through over-regulation. Alternatively, we show that, in several scenarios, rewarding those that follow safety measures may increase the development speed while ensuring safe choices. Moreover, in {the latter} regimes, rewards do not suffer from the issue of over-regulation as is the case for punishment. Overall, our findings provide valuable insights into the nature and kinds of regulatory actions most suitable to improve safety compliance in the contexts of both smooth and sudden technological shifts.

cs.AI↗

arXiv2020

Timing uncertainty in collective risk dilemmas encourages group reciprocation and polarization

Human social dilemmas are often shaped by actions involving uncertain goals and returns that may only be achieved in the future. Climate action, voluntary vaccination and other prospective choices stand as paramount examples of this setting. In this context, as well as in many other social dilemmas, uncertainty may produce non-trivial effects. Whereas uncertainty about collective targets and their impact were shown to negatively affect group coordination and success, no information is available about timing uncertainty, i.e. how uncertainty about when the target needs to be reached affects the outcome as well as the decision-making. Here we show experimentally, through a collective dilemma wherein groups of participants need to avoid a tipping point under the risk of collective loss, that timing uncertainty prompts not only early generosity but also polarized contributions, in which participants' total contributions are distributed more unfairly than when there is no uncertainty. Analyzing participant behavior reveals, under uncertainty, an increase in reciprocal strategies wherein contributions are conditional on the previous donations of the other participants, a group analogue of the well-known Tit-for-Tat strategy. Although large timing uncertainty appears to reduce collective success, groups that successfully collect the required amount show strong reciprocal coordination. This conclusion is supported by a game theoretic model examining the dominance of behaviors in case of timing uncertainty. In general, timing uncertainty casts a shadow on the future that leads participants to respond early, encouraging reciprocal behaviors, and unequal contributions.

physics.soc-ph↗

arXiv2020

To regulate or not: a social dynamics analysis of the race for AI supremacy

Rapid technological advancements in AI as well as the growing deployment of intelligent technologies in new application domains are currently driving the competition between businesses, nations and regions. This race for technological supremacy creates a complex ecology of choices that may lead to negative consequences, in particular, when ethical and safety procedures are underestimated or even ignored. As a consequence, different actors are urging to consider both the normative and social impact of these technological advancements. As there is no easy access to data describing this AI race, theoretical models are necessary to understand its dynamics, allowing for the identification of when, how and which procedures need to be put in place to favour outcomes beneficial for all. We show that, next to the risks of setbacks and being reprimanded for unsafe behaviour, the time-scale in which AI supremacy can be achieved plays a crucial role. When this supremacy can be achieved in a short term, those who completely ignore the safety precautions are bound to win the race but at a cost to society, apparently requiring regulatory actions. Our analysis reveals that blindly imposing regulations may not have anticipated effect as only for specific conditions a dilemma arises between what individually preferred and globally beneficial. Similar observations can be made for the long-term development case. Yet different from the short term situation, certain conditions require the promotion of risk-taking as opposed to compliance to safety regulations in order to improve social welfare. These results remain robust when two or several actors are involved in the race and when collective rather than individual setbacks are produced by risk-taking behaviour. When defining codes of conduct and regulatory policies for AI, a clear understanding about the time-scale of the race is required.

cs.CY↗

arXiv2019

Towards a phylogenetic measure to quantify HIV incidence

One of the cornerstones in combating the HIV pandemic is being able to assess the current state and evolution of local HIV epidemics. This remains a complex problem, as many HIV infected individuals remain unaware of their infection status, leading to parts of HIV epidemics being undiagnosed and under-reported. To that end, we firstly present a method to learn epidemiological parameters from phylogenetic trees, using approximate Bayesian computation (ABC). The epidemiological parameters learned as a result of applying ABC are subsequently used in epidemiological models that aim to simulate a specific epidemic. Secondly, we continue by describing the development of a tree statistic, rooted in coalescent theory, which we use to relate epidemiological parameters to a phylogenetic tree, by using the simulated epidemics. We show that the presented tree statistic enables differentiation of epidemiological parameters, while only relying on phylogenetic trees, thus enabling the construction of new methods to ascertain the epidemiological state of an HIV epidemic. By using genetic data to infer epidemic sizes, we expect to enhance understanding of the portions of the infected population in which diagnosis rates are low.

q-bio.PE↗

arXiv2019

Dynamic Weights in Multi-Objective Deep Reinforcement Learning

Many real-world decision problems are characterized by multiple conflicting objectives which must be balanced based on their relative importance. In the dynamic weights setting the relative importance changes over time and specialized algorithms that deal with such change, such as a tabular Reinforcement Learning (RL) algorithm by Natarajan and Tadepalli (2005), are required. However, this earlier work is not feasible for RL settings that necessitate the use of function approximators. We generalize across weight changes and high-dimensional inputs by proposing a multi-objective Q-network whose outputs are conditioned on the relative importance of objectives and we introduce Diverse Experience Replay (DER) to counter the inherent non-stationarity of the Dynamic Weights setting. We perform an extensive experimental evaluation and compare our methods to adapted algorithms from Deep Multi-Task/Multi-Objective Reinforcement Learning and show that our proposed network in combination with DER dominates these adapted algorithms across weight change scenarios and problem domains.

cs.LG↗

arXiv2016

Modeling contact networks of patients and MRSA spread in Swedish hospitals

Methicillin-resistant Staphylococcus aureus (MRSA) is a difficult-to-treat infection that only in the European Union affects about 150,000 patients and causes extra costs of 380 million Euros annually to the health-care systems. Increasing efforts have been taken to mitigate the epidemics and to avoid potential outbreaks in low endemic settings. Understanding the population dynamics of MRSA through modeling is essential to identify the causal mechanisms driving the epidemics and to generalize conclusions to different contexts. We develop an innovative high-resolution spatiotemporal contact network model of interactions between patients to reproduce the hospital population in the context of the Stockholm County in Sweden and simulate the spread of MRSA within this population. Our model captures the spatial and temporal heterogeneity caused by human behavior and by the dynamics of mobility within wards and hospitals. We estimate that in this population the epidemic threshold is at about 0.008. We also identify that these heterogeneous contact patterns cause the emergence of super-spreader patients and a polynomial growth of the epidemic curve. We finally study the effect of standard intervention control strategies and identify that screening is more effective than improved hygienic in order to cause smaller or null outbreaks.

q-bio.PE↗

arXiv2007

Evolution of Complexity

The evolution of complexity has been a central theme for Biology [2] and Artificial Life research [1]. It is generally agreed that complexity has increased in our universe, giving way to life, multi-cellularity, societies, and systems of higher complexities. However, the mechanisms behind the complexification and its relation to evolution are not well understood. Moreover complexification can be used to mean different things in different contexts. For example, complexification has been interpreted as a process of diversification between evolving units [2] or as a scaling process related to the idea of transitions between different levels of complexity [7]. Understanding the difference or overlap between the mechanisms involved in both situations is mandatory to create acceptable synthetic models of the process, as is required in Artificial Life research. (...)

q-bio.PE↗

arXiv2006

Evolution of Complexity: Introduction to the Workshop

The evolution of complexity has been a central theme for Biology and Artificial Life (Bonner, 1988; Bedau et al., 2000). Complexification has been interpreted in different ways: as a process of diversification between evolving units (Bonner, 1988) or as a scaling process that is related to the idea of transitions between different levels of complexity (Smith and Szathmary, 1995). There have been previous workshops on this topic, e.g. (Heylighen et al., 1999; Lenaerts et al., 2002), but many open questions still remain. Trying to answer these questions from a general perspective might not immediately produce concrete answers for the different fields that are interested in this topic. Consequently, this workshop is organised with a particular focus in mind: The emergence of complexity through evolutionary mechanisms. Primarily we want to have a discussion on evolutionary and related dynamics as mechanisms for producing complexity. Furthermore, we want to bring together historical and novel research in this context.

nlin.AO↗