arXiv subjects

The Anh Han

Publications and source records attributed to The Anh Han.

At least 55 records · Page 3Linked to original sources

arXiv2025

Words are not Wind -- How Public Joint Commitment and Reputation Solve the Prisoner's Dilemma

To achieve common goals, we often use joint commitments. Our commitment helps us to coordinate with our partners and assures them that their cooperative efforts will benefit themselves. However, if one of us can exploit the other's cooperation (as in the Prisoner's Dilemma), our commitment appears less useful. It cannot remove the temptation for our partners to exploit us. Using methods from evolutionary game theory, we study the function of joint commitments in the Prisoner's Dilemma. We propose a reputation system akin to indirect reciprocity, wherein agents observe interactions even when not directly involved. They judge cooperation as good and defection as bad, but, crucially, only if the parties involved had committed to cooperate. This results in stable cooperation even though judgments are made privately, which had been a weakness in previous models of indirect reciprocity. Our work shows that joint commitments have utility beyond coordination problems, which could explain their prevalence. The proposed link between joint commitments and reputation could also explain why some joint commitments are pointedly public, like wedding vows. A reputation-based mechanism might have been particularly relevant in our distant past, in which no institutions existed to enforce commitments.

cs.GT↗

arXiv2025

Multi-Agent Risks from Advanced AI

The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These systems pose novel and under-explored risks. In this report, we provide a structured taxonomy of these risks by identifying three key failure modes (miscoordination, conflict, and collusion) based on agents' incentives, as well as seven key risk factors (information asymmetries, network effects, selection pressures, destabilising dynamics, commitment problems, emergent agency, and multi-agent security) that can underpin them. We highlight several important instances of each risk, as well as promising directions to help mitigate them. By anchoring our analysis in a range of real-world examples and experimental evidence, we illustrate the distinct challenges posed by multi-agent systems and their implications for the safety, governance, and ethics of advanced AI.

cs.MA↗

arXiv2025

Benchmarking Classical, Deep, and Generative Models for Human Activity Recognition

Human Activity Recognition (HAR) has gained significant importance with the growing use of sensor-equipped devices and large datasets. This paper evaluates the performance of three categories of models : classical machine learning, deep learning architectures, and Restricted Boltzmann Machines (RBMs) using five key benchmark datasets of HAR (UCI-HAR, OPPORTUNITY, PAMAP2, WISDM, and Berkeley MHAD). We assess various models, including Decision Trees, Random Forests, Convolutional Neural Networks (CNN), and Deep Belief Networks (DBNs), using metrics such as accuracy, precision, recall, and F1-score for a comprehensive comparison. The results show that CNN models offer superior performance across all datasets, especially on the Berkeley MHAD. Classical models like Random Forest do well on smaller datasets but face challenges with larger, more complex data. RBM-based models also show notable potential, particularly for feature learning. This paper offers a detailed comparison to help researchers choose the most suitable model for HAR tasks.

cs.CV↗

arXiv2024

Enhancing Cancer Diagnosis with Explainable & Trustworthy Deep Learning Models

This research presents an innovative approach to cancer diagnosis and prediction using explainable Artificial Intelligence (XAI) and deep learning techniques. With cancer causing nearly 10 million deaths globally in 2020, early and accurate diagnosis is crucial. Traditional methods often face challenges in cost, accuracy, and efficiency. Our study develops an AI model that provides precise outcomes and clear insights into its decision-making process, addressing the "black box" problem of deep learning models. By employing XAI techniques, we enhance interpretability and transparency, building trust among healthcare professionals and patients. Our approach leverages neural networks to analyse extensive datasets, identifying patterns for cancer detection. This model has the potential to revolutionise diagnosis by improving accuracy, accessibility, and clarity in medical decision-making, possibly leading to earlier detection and more personalised treatment strategies. Furthermore, it could democratise access to high-quality diagnostics, particularly in resource-limited settings, contributing to global health equity. The model's applications extend beyond cancer diagnosis, potentially transforming various aspects of medical decision-making and saving millions of lives worldwide.

cs.AI↗

arXiv2024

Quantifying detection rates for dangerous capabilities: a theoretical model of dangerous capability evaluations

We present a quantitative model for tracking dangerous AI capabilities over time. Our goal is to help the policy and research community visualise how dangerous capability testing can give us an early warning about approaching AI risks. We first use the model to provide a novel introduction to dangerous capability testing and how this testing can directly inform policy. Decision makers in AI labs and government often set policy that is sensitive to the estimated danger of AI systems, and may wish to set policies that condition on the crossing of a set threshold for danger. The model helps us to reason about these policy choices. We then run simulations to illustrate how we might fail to test for dangerous capabilities. To summarise, failures in dangerous capability testing may manifest in two ways: higher bias in our estimates of AI danger, or larger lags in threshold monitoring. We highlight two drivers of these failure modes: uncertainty around dynamics in AI capabilities and competition between frontier AI labs. Effective AI policy demands that we address these failure modes and their drivers. Even if the optimal targeting of resources is challenging, we show how delays in testing can harm AI policy. We offer preliminary recommendations for building an effective testing ecosystem for dangerous capabilities and advise on a research agenda.

cs.AI↗

arXiv2024

Evolutionary dynamics with random payoff matrices

Uncertainty, characterised by randomness and stochasticity, is ubiquitous in applications of evolutionary game theory across various fields, including biology, economics and social sciences. The uncertainty may arise from various sources such as fluctuating environments, behavioural errors or incomplete information. Incorporating uncertainty into evolutionary models is essential for enhancing their relevance to real-world problems. In this perspective article, we survey the relevant literature on evolutionary dynamics with random payoff matrices, with an emphasis on continuous models. We also pose challenging open problems for future research in this important area.

q-bio.PE↗

arXiv2024

Random evolutionary games and random polynomials

In this paper, we discover that the class of random polynomials arising from the equilibrium analysis of random asymmetric evolutionary games is \textit{exactly} the Kostlan-Shub-Smale system of random polynomials, revealing an intriguing connection between evolutionary game theory and the theory of random polynomials. Through this connection, we analytically characterize the statistics of the number of internal equilibria of random asymmetric evolutionary games, namely its mean value, probability distribution, central limit theorem and universality phenomena. Biologically, these quantities enable prediction of the levels of social and biological diversity as well as the overall complexity in a dynamical system. By comparing symmetric and asymmetric random games, we establish that symmetry in group interactions increases the expected number of internal equilibria. Our research establishes new theoretical understanding of asymmetric evolutionary games and highlights the significance of symmetry and asymmetry in group interactions.

math.PR↗

arXiv2024

Evolutionary mechanisms that promote cooperation may not promote social welfare

Understanding the emergence of prosocial behaviours among self-interested individuals is an important problem in many scientific disciplines. Various mechanisms have been proposed to explain the evolution of such behaviours, primarily seeking the conditions under which a given mechanism can induce highest levels of cooperation. As these mechanisms usually involve costs that alter individual payoffs, it is however possible that aiming for highest levels of cooperation might be detrimental for social welfare -- the later broadly defined as the total population payoff, taking into account all costs involved for inducing increased prosocial behaviours. Herein, by comparatively analysing the social welfare and cooperation levels obtained from stochastic evolutionary models of two well-established mechanisms of prosocial behaviour, namely, peer and institutional incentives, we demonstrate exactly that. We show that the objectives of maximising cooperation levels and the objectives of maximising social welfare are often misaligned. We argue for the need of adopting social welfare as the main optimisation objective when designing and implementing evolutionary mechanisms for social and collective goods.

math.DS↗

arXiv2024

Trust AI Regulation? Discerning users are vital to build trust and effective AI regulation

There is general agreement that some form of regulation is necessary both for AI creators to be incentivised to develop trustworthy systems, and for users to actually trust those systems. But there is much debate about what form these regulations should take and how they should be implemented. Most work in this area has been qualitative, and has not been able to make formal predictions. Here, we propose that evolutionary game theory can be used to quantitatively model the dilemmas faced by users, AI creators, and regulators, and provide insights into the possible effects of different regulatory regimes. We show that creating trustworthy AI and user trust requires regulators to be incentivised to regulate effectively. We demonstrate the effectiveness of two mechanisms that can achieve this. The first is where governments can recognise and reward regulators that do a good job. In that case, if the AI system is not too risky for users then some level of trustworthy development and user trust evolves. We then consider an alternative solution, where users can condition their trust decision on the effectiveness of the regulators. This leads to effective regulation, and consequently the development of trustworthy AI and user trust, provided that the cost of implementing regulations is not too high. Our findings highlight the importance of considering the effect of different regulatory regimes from an evolutionary game theoretic perspective.

cs.AI↗

arXiv2024

Evolution of commitment in the spatial Public Goods Game through institutional incentives

Studying social dilemmas prompts the question of how cooperation can emerge in situations where individuals are expected to act selfishly. Here, in the framework of the one-shot Public Goods Game (PGG), we introduce the concept that individuals can potentially adjust their behaviour based on the cooperative commitments made by other players in the group prior to the actual PGG interaction. To this end, we establish a commitment threshold that group members must meet for a commitment to be formed. We explore the effects of punishing commitment non-compliant players (those who commit and defect if the commitment is formed) and rewarding commitment-compliant players (those who commit and cooperate if the commitment is formed). In the presence of commitment and absence of an incentive mechanism, we observe that conditional behaviour based on commitment alone can enhance cooperation, especially when considering a specific commitment threshold value. In the presence of punishment, our findings suggest that the survival of cooperation most likely happen at intermediate commitment thresholds. Notably, cooperation is maximised at high thresholds, when punishment occurs more frequently. We also see that when cooperation rarely survives, a cyclic behaviour emerges, facilitating the persistence of cooperation. For the reward case, we found that cooperation is highly frequent regardless of the commitment threshold adopted.

physics.soc-ph↗

arXiv2023

Evolutionary game theory: the mathematics of evolution and collective behaviours

This brief discusses evolutionary game theory as a powerful and unified mathematical tool to study evolution of collective behaviours. It summarises some of my recent research directions using evolutionary game theory methods, which include i) the analysis of statistical properties of the number of (stable) equilibria in a random evolutionary game, and ii) the modelling of safety behaviours' evolution and the risk posed by advanced Artificial Intelligence technologies in a technology development race. Finally, it includes an outlook and some suggestions for future researchers.

cs.MA↗

arXiv2023

Discriminatory or Samaritan -- which AI is needed for humanity? An Evolutionary Game Theory Analysis of Hybrid Human-AI populations

As artificial intelligence (AI) systems are increasingly embedded in our lives, their presence leads to interactions that shape our behaviour, decision-making, and social interactions. Existing theoretical research has primarily focused on human-to-human interactions, overlooking the unique dynamics triggered by the presence of AI. In this paper, resorting to methods from evolutionary game theory, we study how different forms of AI influence the evolution of cooperation in a human population playing the one-shot Prisoner's Dilemma game in both well-mixed and structured populations. We found that Samaritan AI agents that help everyone unconditionally, including defectors, can promote higher levels of cooperation in humans than Discriminatory AI that only help those considered worthy/cooperative, especially in slow-moving societies where change is viewed with caution or resistance (small intensities of selection). Intuitively, in fast-moving societies (high intensities of selection), Discriminatory AIs promote higher levels of cooperation than Samaritan AIs.

cs.MA↗

arXiv2023

We both think you did wrong -- How agreement shapes and is shaped by indirect reciprocity

Humans judge each other's actions, which at least partly functions to detect and deter cheating and to enable helpfulness in an indirect reciprocity fashion. However, most forms of judging do not only concern the action itself, but also the moral status of the receiving individual (to deter cheating it must be morally acceptable to withhold help from cheaters). This is a problem, when not everybody agrees who is good and who is bad. Although it has been widely acknowledged that disagreement may exist and that it can be detrimental for indirect reciprocity, the details of this crucial feature of moral judgments have never been studied in depth. We show, that even when everybody assesses individually (aka privately), some moral judgement systems (aka norms) can lead to high levels of agreement. We give a detailed account of the mechanisms which cause it and we show how to predict agreement analytically without requiring agent-based simulations, and for any observation rate. Finally, we show that agreement may increase or decrease reputations and therefore how much helpfulness (aka cooperation) occurs.

physics.soc-ph↗

arXiv2023

Both eyes open: Vigilant Incentives help Regulatory Markets improve AI Safety

In the context of rapid discoveries by leaders in AI, governments must consider how to design regulation that matches the increasing pace of new AI capabilities. Regulatory Markets for AI is a proposal designed with adaptability in mind. It involves governments setting outcome-based targets for AI companies to achieve, which they can show by purchasing services from a market of private regulators. We use an evolutionary game theory model to explore the role governments can play in building a Regulatory Market for AI systems that deters reckless behaviour. We warn that it is alarmingly easy to stumble on incentives which would prevent Regulatory Markets from achieving this goal. These 'Bounty Incentives' only reward private regulators for catching unsafe behaviour. We argue that AI companies will likely learn to tailor their behaviour to how much effort regulators invest, discouraging regulators from innovating. Instead, we recommend that governments always reward regulators, except when they find that those regulators failed to detect unsafe behaviour that they should have. These 'Vigilant Incentives' could encourage private regulators to find innovative ways to evaluate cutting-edge AI systems.

cs.AI↗

arXiv2023

Does Spending More Always Ensure Higher Cooperation? An Analysis of Institutional Incentives on Heterogeneous Networks

Humans have developed considerable machinery used at scale to create policies and to distribute incentives, yet we are forever seeking ways in which to improve upon these, our institutions. Especially when funding is limited, it is imperative to optimise spending without sacrificing positive outcomes, a challenge which has often been approached within several areas of social, life and engineering sciences. These studies often neglect the availability of information, cost restraints, or the underlying complex network structures, which define real-world populations. Here, we have extended these models, including the aforementioned concerns, but also tested the robustness of their findings to stochastic social learning paradigms. Akin to real-world decisions on how best to distribute endowments, we study several incentive schemes, which consider information about the overall population, local neighbourhoods, or the level of influence which a cooperative node has in the network, selectively rewarding cooperative behaviour if certain criteria are met. Following a transition towards a more realistic network setting and stochastic behavioural update rule, we found that carelessly promoting cooperators can often lead to their downfall in socially diverse settings. These emergent cyclic patterns not only damage cooperation, but also decimate the budgets of external investors. Our findings highlight the complexity of designing effective and cogent investment policies in socially diverse populations.

cs.MA↗

arXiv2022

Social Diversity Reduces the Complexity and Cost of Fostering Fairness

Institutions and investors are constantly faced with the challenge of appropriately distributing endowments. No budget is limitless and optimising overall spending without sacrificing positive outcomes has been approached and resolved using several heuristics. To date, prior works have failed to consider how to encourage fairness in a population where social diversity is ubiquitous, and in which investors can only partially observe the population. Herein, by incorporating social diversity in the Ultimatum game through heterogeneous graphs, we investigate the effects of several interference mechanisms which assume incomplete information and flexible standards of fairness. We quantify the role of diversity and show how it reduces the need for information gathering, allowing us to relax a strict, costly interference process. Furthermore, we find that the influence of certain individuals, expressed by different network centrality measures, can be exploited to further reduce spending if minimal fairness requirements are lowered. Our results indicate that diversity changes and opens up novel mechanisms available to institutions wishing to promote fairness. Overall, our analysis provides novel insights to guide institutional policies in socially diverse complex systems.

cs.MA↗

arXiv2022

Understanding Emergent Behaviours in Multi-Agent Systems with Evolutionary Game Theory

The mechanisms of emergence and evolution of collective behaviours in dynamical Multi-Agent Systems (MAS) of multiple interacting agents, with diverse behavioral strategies in co-presence, have been undergoing mathematical study via Evolutionary Game Theory (EGT). Their systematic study also resorts to agent-based modelling and simulation (ABM) techniques, thus enabling the study of aforesaid mechanisms under a variety of conditions, parameters, and alternative virtual games. This paper summarises some main research directions and challenges tackled in our group, using methods from EGT and ABM. These range from the introduction of cognitive and emotional mechanisms into agents' implementation in an evolving MAS, to the cost-efficient interference for promoting prosocial behaviours in complex networks, to the regulation and governance of AI safety development ecology, and to the equilibrium analysis of random evolutionary multi-player games. This brief aims to sensitize the reader to EGT based issues, results and prospects, which are accruing in importance for the modeling of minds with machines and the engineering of prosocial behaviours in dynamical MAS, with impact on our understanding of the emergence and stability of collective behaviours. In all cases, important open problems in MAS research as viewed or prioritised by the group are described.

cs.AI↗

arXiv2022

Institutional Incentives for the Evolution of Committed Cooperation: Ensuring Participation is as Important as Enhancing Compliance

Both conventional wisdom and empirical evidence suggests that arranging a prior commitment or agreement before an interaction enhances the chance of reaching mutual cooperation. Yet it is not clear what mechanisms can promote the participation in and compliance with such a commitment, especially when the former is costly and deviating from the latter is profitable. Prior work either considers regimented commitments where compensation is assumed enforceable from dishonest committers, or assume implicit commitments from every individual (so they are all in and thus being treated as such). Here we develop a theory of participation and compliance with respect to an explicit prior commitment under institutional incentives where individuals, at first, decide whether or not to join a cooperative agreement to play a one-shot social dilemma game. Using a mathematical model, we determine when participating in a costly commitment and complying with it, is an evolutionary stable strategy (ESS) when playing against all other possible strategies, and results in high levels of cooperation in the population. We show that, given a sufficient budget for providing incentives, reward of commitment compliant behaviours better promotes cooperation than punishment of non-compliant ones. Moreover, by sparing part of this budget for rewarding those who are willing to participate in a commitment, the overall frequency of cooperation can be significantly enhanced, for both reward and punishment. Finally, we find that, surprisingly, the presence of errors in a participation decision favours evolutionary stability of commitment compliant strategies and higher levels of cooperation.

math.DS↗