This chapter contains sections titled: Introduction My Theory of Moral Theory The Structure of Some Moral Theories Exemplarism A Comprehensive Exemplarist Virtue Theory References.

The emerging discipline of Machine Ethics is concerned with creating autonomous artificial moral agents that perform ethically significant actions out in the world. Recently, Wallach and Allen (Moral machines: teaching robots right from wrong, Oxford University Press, Oxford, 2009) and others have argued that a virtue-based moral framework is a promising tool for meeting this end. However, even if we could program autonomous machines to follow a virtue-based moral framework, there are certain pressing ethical issues that need to be taken (...) into account, prior to the implementation and development stages. Here I examine whether the creation of virtuous autonomous machines is morally permitted by the central tenets of virtue ethics. It is argued that the creation of such machines violates certain tenets of virtue ethics, and hence that the creation and use of those machines is impermissible. One upshot of this is that, although virtue ethics may have a role to play in certain near-term Machine Ethics projects (e.g. designing systems that are sensitive to ethical considerations), machine ethicists need to look elsewhere for a moral framework to implement into their autonomous artificial moral agents, Wallach and Allen’s claims notwithstanding. (shrink)

This book explores the role of artificial intelligence in the development of a claim that morality is person-made and rational. Professor Danielson builds moral robots that do better than amoral competitors in a tournament of games like the Prisoners Dilemma and Chicken. The book thus engages in current controversies over the adequacy of the received theory of rational choice. It sides with Gauthier and McClennan, who extend the devices of rational choice to include moral constraint. Artificial Morality goes further, by (...) promoting communication, testing and copying of principles and by stressing empirical tests. (shrink)

Virtue ethics has many times been suggested as a promising recipe for the construction of artificial moral agents due to its emphasis on moral character and learning. However, given the complex nature of the theory, hardly any work has de facto attempted to implement the core tenets of virtue ethics in moral machines. The main goal of this paper is to demonstrate how virtue ethics can be taken all the way from theory to machine implementation. To achieve this goal, we (...) critically explore the possibilities and challenges for virtue ethics from a computational perspective. Drawing on previous conceptual and technical work, we outline a version of artificial virtue based on moral functionalism, connectionist bottom–up learning, and eudaimonic reward. We then describe how core features of the outlined theory can be interpreted in terms of functionality, which in turn informs the design of components necessary for virtuous cognition. Finally, we present a comprehensive framework for the technical development of artificial virtuous agents and discuss how they can be implemented in moral environments. (shrink)

Virtue ethics has many times been suggested as a promising recipe for the construction of artificial moral agents due to its emphasis on moral character and learning. However, given the complex nature of the theory, hardly any work has de facto attempted to implement the core tenets of virtue ethics in moral machines. The main goal of this paper is to demonstrate how virtue ethics can be taken all the way from theory to machine implementation. To achieve this goal, we (...) critically explore the possibilities and challenges for virtue ethics from a computational perspective. Drawing on previous conceptual and technical work, we outline a version of artificial virtue based on moral functionalism, connectionist bottom–up learning, and eudaimonic reward. We then describe how core features of the outlined theory can be interpreted in terms of functionality, which in turn informs the design of components necessary for virtuous cognition. Finally, we present a comprehensive framework for the technical development of artificial virtuous agents and discuss how they can be implemented in moral environments. (shrink)

Offers a critique of prevalent approaches to human good and virtue. Slote shows that typical philosophical accounts of the virtues and human goods oversimplify the subject and that a more exact approach is needed.

In this book, Slote offers the first full-scale foundational account of virtue ethics to have appeared since the recent revival of interest in the ethics of virtue. Slote advocates a particular form of such ethics for its intuitive and structural advantages over Kantianism, utilitarianism, and common-sense morality, and he argues that the problems of other views can be avoided and a contemporary plausible version of virtue ethics achieved only by abandoning specifically moral concepts for general aretaic notions like admirability and (...) virtue. Although this study is not bound by particular Aristotelian doctrines, it places an Aristotelian emphasis on both self-benefiting and other-benefiting virtues. Slote criticizes Kantian and common-sense morality for internal incoherencies and for downgrading the moral individual and her well-being in some previously unnoticed ways. By contrast, this book defends a distinctive, intuitive, and symmetric ethical principle according to which we should balance self-concern with concern for others, but it also concludes that there is, contrary to utilitarianism, no single basis for status as a virtue nor any simple relation between the virtues and human well-being. (shrink)

Julia Annas offers a new account of virtue and happiness as central ethical ideas. She argues that exercising a virtue involves practical reasoning of the kind we find in someone exercising an everyday practical skill, such as farming, building, or playing the piano. This helps us to see virtue as part of an agent's happiness or flourishing.

Role morality can be defined as “claim(ing) a moral permission to harm others in ways that, if not for the role, would be wrong” (A. Applbaum: 1999, Ethics for Adversaries: The Morality of Roles in Public and Professional Life (Princeton University Press, Princeton, NJ) p. 3). Adversarial situations resulting in role morality occur most frequently in the fields of law, business, and government. Within the realm of accounting, professional obligations may place the accountant in a situation where he/she is susceptible (...) to the pressures of role morality. If the accountant engages in acts consistent with role morality, significant harm to others may result. The current study represents an initial investigation into role morality in accounting and includes survey data from three samples of professionals: accountants, physicians, and attorneys. Results suggest that accountants generally do not agree that role morality is acceptable. Additionally, when compared to the groups of physicians and attorneys, physicians agree the least with role morality, while attorneys agree the most. Implications for practicing accountants and suggestions for future research into the theory of role morality are offered. (shrink)

The essays in this volume represent the first steps by philosophers and artificial intelligence researchers toward explaining why it is necessary to add an ...

Source: "This book addresses the fundamentals of machine ethics. It discusses abilities required for ethical machine reasoning and the programming features that enable them. It connects ethics, psychological ethical processes, and machine implemented procedures. From a technical point of view, the book uses logic programming and evolutionary game theory to model and link the individual and collective moral realms. It also reports on the results of experiments performed using several model implementations. Opening specific and promising inroads into the terra incognita (...) of machine ethics, the authors define here new tools and describe a variety of program-tested moral applications and implemented systems. In addition, they provide alternative readings paths, allowing readers to best focus on their specific interests and to explore the concepts at different levels of detail. Mainly written for researchers in cognitive science, artificial intelligence, robotics, philosophy of technology and engineering of ethics, the book will also be of general interest to other academics, undergraduates in search of research topics, science journalists as well as science and society forums, legislators and military organizations concerned with machine ethics.". (shrink)

At the end of a thoughtful article on the future of nuclear war, Wiesner and York concluded that: "Both sides in the arms race are... confronted by the dilemma of steadily increasing military power and steadily decreasing national security. It is our considered professional judgment that this dilemma has no technical solution. If the great powers continue to look for solutions in the area of science and technology only, the result will be to worsen the situation.".

The author presents and defends three theses: (1) "the first is that it is not profitable for us at present to do moral philosophy; that should be laid aside at any rate until we have an adequate philosophy of psychology." (2) "the second is that the concepts of obligation, And duty... And of what is morally right and wrong, And of the moral sense of 'ought', Ought to be jettisoned if this is psychologically possible...." (3) "the third thesis is that (...) the differences between the well-Known english writers on moral philosophy from sidgwick to the present day are of little importance." (staff). (shrink)

Virtue ethics is perhaps the most important development within late twentieth-century moral philosophy. Rosalind Hursthouse, who has made notable contributions to this development, here presents a full exposition and defense of her neo-Aristotelian version of virtue ethics. She shows how virtue ethics can provide guidance for action, illuminate moral dilemmas, and bring out the moral significance of the emotions.

This volume brings together much of the most influential work undertaken in the field of virtue ethics over the last four decades. The ethics of virtue predominated in the ancient world, and recent moral philosophy has seen a revival of interest in virtue ethics as a rival to Kantian and utilitarian approaches to morality. Divided into four sections, the collection includes articles critical of other traditions; early attempts to offer a positive vision of virtue ethics; some later criticisms of the (...) revival of virtue ethics; and, finally, some recent, more theoretically ambitious essays in virtue ethics. (shrink)

Robot ethics encompasses ethical questions about how humans should design, deploy, and treat robots; machine morality encompasses questions about what moral capacities a robot should have and how these capacities could be computationally implemented. Publications on both of these topics have doubled twice in the past 10 years but have often remained separate from one another. In an attempt to better integrate the two, I offer a framework for what a morally competent robot would look like and discuss a number (...) of ethical questions about the design, use, and treatment of such moral robots in society. Instead of searching for a fixed set of criteria of a robot’s moral competence I identify the multiple elements that make up human moral competence and probe the possibility of designing robots that have one or more of these human elements, which include: moral vocabulary; a system of norms; moral cognition and affect; moral decision making and action; moral communication. Juxtaposing empirical research, philosophical debates, and computational challenges, this article adopts an optimistic perspective: if robotic design truly commits to building morally competent robots, then those robots could be trustworthy and productive partners, caretakers, educators, and members of the human community. Moral competence does not resolve all ethical concerns over robots in society, but it may be a prerequisite to resolve at least some of them. (shrink)

As artificial intelligence (AI) continues to proliferate into every area of modern life, there is no doubt that society has to think deeply about the potential impact, whether negative or positive, that it will have. Whilst scholars recognise that AI can usher in a new era of personal, social and economic prosperity, they also warn of the potential for it to be misused towards the detriment of society. Deliberate strategies are therefore required to ensure that AI can be safely integrated (...) into society in a manner that would maximise the good for as many people as possible, whilst minimising the bad. One of the most urgent societal expectations of artificial agents is the need for them to behave in a manner that is morally relevant, i.e. to become artificial moral agents (AMAs). In this article, I will argue that exemplarism, an ethical theory based on virtue ethics, can be employed in the building of computationally rational AMAs with weak machine ethics. I further argue that three features of exemplarism, namely grounding in moral exemplars, meeting community expectations and practical simplicity, are crucial to its uniqueness and suitability for application in building AMAs that fit the ethos of AI4SG. (shrink)

This paper argues for the moral significance of the notion of an evil person or character. First, I argue that accounts of evil character ought to support a robust bad/evil distinction; yet existing theories cannot plausibly do so. Consequentialist and related theories also fail to account for some crucial properties of evil persons. Second, I sketch an intuitively plausible “affective-motivational” account of evil character. Third, I argue that the notion of evil character, thus conceived, denotes a significant moral category. It (...) marks one end of a moral continuum that has, at the opposite pole, the saint. Fourth, I argue that “frequent evildoing” accounts confuse this moral space with another: that defined by the moral hero and the moral criminal. (shrink)

This paper presents the results of training an artificial neural network (ANN) to classify moral situations. The ANN produces a similarity space in the process of solving its classification problem. The state space is subjected to analysis that suggests that holistic approaches to interpreting its functioning are problematic. The idea of a contributory or pro tanto standard, as discussed in debates between moral particularists and generalists, is used to understand the structure of the similarity space generated by the ANN. A (...) spectrum of possibilities for reasons, from atomistic to holistic, is discussed. Reasons are understood as increasing in nonlocality as they move away from atomism. It is argued that contributory standards could be used to understand forms of nonlocality that need not go all the way to holism. It is also argued that contributory standards may help us to understand the kind of similarity at work in analogical reasoning and argument in ethics. Some objections to using state space approaches to similarity are dealt with, as are objections to using empirical and computational work in philosophy. (shrink)

We describe a form of moral artificial intelligence that could be used to improve human moral decision-making. We call it the “artificial moral advisor”. The AMA would implement a quasi-relativistic version of the “ideal observer” famously described by Roderick Firth. We describe similarities and differences between the AMA and Firth’s ideal observer. Like Firth’s ideal observer, the AMA is disinterested, dispassionate, and consistent in its judgments. Unlike Firth’s observer, the AMA is non-absolutist, because it would take into account the human (...) agent’s own principles and values. We argue that the AMA would respect and indeed enhance individuals’ moral autonomy, help individuals achieve wide and a narrow reflective equilibrium, make up for the limitations of human moral psychology in a way that takes conservatives’ objections to human bioenhancement seriously, and implement the positive functions of intuitions and emotions in human morality without their downsides, such as biases and prejudices. (shrink)

Virtue ethics seems to be a promising moral theory for understanding and interpreting the development and behavior of artificial moral agents. Virtuous artificial agents would blur traditional distinctions between different sorts of moral machines and could make a claim to membership in the moral community. Accordingly, we investigate the “machine question” by studying whether virtue or vice can be attributed to artificial intelligence; that is, are people willing to judge machines as possessing moral character? An experiment describes situations where either (...) human or AI agents engage in virtuous or vicious behavior and experiment participants then judge their level of virtue or vice. The scenarios represent different virtue ethics domains of truth, justice, fear, wealth, and honor. Quantitative and qualitative analyses show that moral attributions are weakened for AIs compared to humans, and the reasoning and explanations for the attributions are varied and more complex. On “relational” views of membership in the moral community, virtuous machines would indeed be included, even if they are indeed weakened. Hence, while our moral relationships with artificial agents may be of the same types, they may yet remain substantively different than our relationships to human beings. (shrink)

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive engagement between people working in both domains. Second, it is important to be clear about the goal of alignment. There are significant differences between AI that aligns with instructions, intentions, revealed preferences, ideal preferences, interests and values. A principle-based approach to AI alignment, which combines these elements (...) in a systematic way, has considerable advantages in this context. Third, the central challenge for theorists is not to identify ‘true’ moral principles for AI; rather, it is to identify fair principles for alignment that receive reflective endorsement despite widespread variation in people’s moral beliefs. The final part of the paper explores three ways in which fair principles for AI alignment could potentially be identified. (shrink)

Rosalind Hursthouse has written an excellent book, in which she develops a neo-Aristotelian virtue ethics that she sees as avoiding some of the major criticisms leveled against virtue ethics in general, and against Aristotle's brand of virtue ethics in particular.

The following is a summary of the author’s five-stage model of adult skill acquisition, developed in collaboration with Hubert L. Dreyfus. An earlier version of this article appeared in chapter 1 of Mind Over Machine: The Power of Human Intuition and Expertise in the Era of the Computer (1986, Free Press, New York).

Can a mass of networked neurons produce moral human agents? I shall argue that it can; a brain can be morally excellent. A connectionist account of how the brain works can explain how a person might be morally excellent in Aristotle's sense of the term. According to connectionism, the brain is a maze of interconnections trained to recognize and respond to patterns of stimulation. According to Aristotle, a morally excellent human is a practically wise person trained in good habits. What (...) an Aristotelian theory of ethics and a connectionist theory of mind have in common is the assumption that the successful mind/brain has the disposition to behave appropriately in appropriate circumstances. According to Aristotle, the good person knows the right end, desires and chooses to pursue it, and recognizes the right means to it. Thus the good person's brain must be able to form certain moral concepts, develop appropriate behavioral dispositions, and learn practical reasoning skills. I shall argue that this collection of the brain's cognitive capacities is best accounted for by a connectionist theory of the mind/brain. The human condition is both material and moral; we are brain-controlled bodies with ethical values. My essay seeks to understand the relationship between our brains and our values, between how the brain works and how we make moral decisions. (shrink)

Traditional approaches to computer ethics regard computers as tools, andfocus, therefore, on the ethics of their use. Alternatively, computer ethicsmight instead be understood as a study of the ethics of computationalagents, exploring, for example, the different characteristics and behaviorsthat might benefit such an agent in accomplishing its goals. In this paper,I identify a list of characteristics of computational agents that facilitatetheir pursuit of their end, and claim that these characteristics can beunderstood as virtues within a framework of virtue ethics. This (...) frameworkincludes four broad categories – agentive, social, environmental, and moral– each of which can be understood as a spectrum of virtues rangingbetween two extreme subcategories. Although the use of a virtue frameworkis metaphorical rather than literal, I argue that by providing a frameworkfor identifying and critiquing assumptions about what a `good' computer is,a study of android arete provides focus and direction to the developmentof future computational agents. (shrink)

One of the objectives in the field of artificial intelligence for some decades has been the development of artificial agents capable of coexisting in harmony with people and other systems. The computing research community has made efforts to design artificial agents capable of doing tasks the way people do, tasks requiring cognitive mechanisms such as planning, decision-making, and learning. The application domains of such software agents are evident nowadays. Humans are experiencing the inclusion of artificial agents in their environment as (...) unmanned vehicles, intelligent houses, and humanoid robots capable of caring for people. In this context, research in the field of machine ethics has become more than a hot topic. Machine ethics focuses on developing ethical mechanisms for artificial agents to be capable of engaging in moral behavior. However, there are still crucial challenges in the development of truly Artificial Moral Agents. This paper aims to show the current status of Artificial Moral Agents by analyzing models proposed over the past two decades. As a result of this review, a taxonomy to classify Artificial Moral Agents according to the strategies and criteria used to deal with ethical problems is proposed. The presented review aims to illustrate (1) the complexity of designing and developing ethical mechanisms for this type of agent, and (2) that there is a long way to go (from a technological perspective) before this type of artificial agent can replace human judgment in difficult, surprising or ambiguous moral situations. (shrink)

This paper proposes a methodological redirection of the philosophical debate on artificial moral agency in view of increasingly pressing practical needs due to technological development. This “normative approach” suggests abandoning theoretical discussions about what conditions may hold for moral agency and to what extent these may be met by artificial entities such as AI systems and robots. Instead, the debate should focus on how and to what extent such entities should be included in human practices normally assuming moral agency and (...) responsibility of participants. The proposal is backed up by an analysis of the AMA debate, which is found to be overly caught in the opposition between so-called standard and functionalist conceptions of moral agency, conceptually confused and practically inert. Additionally, we outline some main themes of research in need of attention in light of the suggested normative approach to AMA. (shrink)

Given that artificial moral agents—such as autonomous vehicles, lethal autonomous weapons, and automated financial trading systems—are now part of the socio-ethical equation, we should morally evaluate their behavior. How should artificial moral agents make decisions? Is one moral theory better suited than others for machine ethics? After briefly overviewing the dominant ethical approaches for building morality into machines, this paper discusses a recent proposal, put forward by Don Howard and Ioan Muntean (2016, 2017), for an artificial moral agent based on (...) virtue theory. While the virtuous artificial moral agent has various strengths, this paper argues that a rule-based utilitarian approach (in contrast to a strict act-utilitarian approach) is superior because it can capture the most important features of the virtue-theoretic approach while realizing additional significant benefits. Specifically, a 2-level utilitarian artificial moral agent incorporating both established moral rules and a utility calculator is especially well-suited for machine ethics. (shrink)

Virtue ethics is currently one of three major approaches in normative ethics. It may, initially, be identified as the one that emphasizes the virtues, or moral character, in contrast to the approach that emphasizes duties or rules (deontology) or that emphasizes the consequences of actions (consequentialism). Suppose it is obvious that someone in need should be helped. A utilitarian will point to the fact that the consequences of doing so will maximize well-being, a deontologist to the fact that, in doing (...) so the agent will be acting in accordance with a moral rule such as “Do unto others as you would be done by” and a virtue ethicist to the fact that helping the person would be charitable or benevolent. (shrink)

We propose that virtue ethics can be used to address ethical issues central to discussions about sex robots. In particular, we argue virtue ethics is well equipped to focus on the implications of sex robots for human moral character. Our evaluation develops in four steps. First, we present virtue ethics as a suitable framework for the evaluation of human–robot relationships. Second, we show the advantages of our virtue ethical account of sex robots by comparing it to current instrumentalist approaches, showing (...) how the former better captures the reciprocal interaction between robots and their users. Third, we examine how a virtue ethical analysis of intimate human–robot relationships could inspire the design of robots that support the cultivation of virtues. We suggest that a sex robot which is equipped with a consent-module could support the cultivation of compassion when used in supervised, therapeutic scenarios. Fourth, we discuss the ethical implications of our analysis for user autonomy and responsibility. (shrink)

Computers are already approving financial transactions, controlling electrical supplies, and driving trains. Soon, service robots will be taking care of the elderly in their homes, and military robots will have their own targeting and firing protocols. Colin Allen and Wendell Wallach argue that as robots take on more and more responsibility, they must be programmed with moral decision-making abilities, for our own safety. Taking a fast paced tour through the latest thinking about philosophical ethics and artificial intelligence, the authors argue (...) that even if full moral agency for machines is a long way off, it is already necessary to start building a kind of functional morality, in which artificial moral agents have some basic ethical sensitivity. But the standard ethical theories don't seem adequate, and more socially engaged and engaging robots will be needed. As the authors show, the quest to build machines that are capable of telling right from wrong has begun. -/- Moral Machines is the first book to examine the challenge of building artificial moral agents, probing deeply into the nature of human decision making and ethics. (shrink)

The 'Evolution of Cooperation' addresses a simple yet age-old question; If living things evolve through competition, how can cooperation ever emerge? Despite the abundant evidence of cooperation all around us, there existed no purely naturalistic answer to this question until 1979, when Robert Axelrod famously ran a computer tournament featuring a standard game-theory exercise called The Prisoner's Dilemma. To everyone's surprise, the program that won the tournament, named Tit for Tat, was not only the simplest but the most "cooperative" entrant. (...) This unexpected victory proved that cooperation - one might even say altruism - is mathematically possible and therefore needs no hidden hand or divine agent to create and sustain it. A great roadblock to the understanding of all sorts of behavior was at last removed. The updated edition includes an extensive new chapter on cooperation in cancer cells and among terrorist organizations. (shrink)

Ethics for Robots describes and defends a method for designing and evaluating ethics algorithms for autonomous machines, such as self-driving cars and search and rescue drones. Derek Leben argues that such algorithms should be evaluated by how effectively they accomplish the problem of cooperation among self-interested organisms, and therefore, rather than simulating the psychological systems that have evolved to solve this problem, engineers should be tackling the problem itself, taking relevant lessons from our moral psychology. Leben draws on the moral (...) theory of John Rawls, arguing that normative moral theories are attempts to develop optimal solutions to the problem of cooperation. He claims that Rawlsian Contractarianism leads to the 'Maximin' principle - the action that maximizes the minimum value - and that the Maximin principle is the most effective solution to the problem of cooperation. He contrasts the Maximin principle with other principles and shows how they can often produce non-cooperative results. Using real-world examples - such as an autonomous vehicle facing a situation where every action results in harm, home care machines, and autonomous weapons systems - Leben contrasts Rawlsian algorithms with alternatives derived from utilitarianism and natural rights libertarianism. Including chapter summaries and a glossary of technical terms, Ethics for Robots is essential reading for philosophers, engineers, computer scientists, and cognitive scientists working on the problem of ethics for autonomous systems. (shrink)

A simple recurrent artificial neural network is used to classify situations as permissible or impermissible. The trained ANN can be understood as having set up a similarity space of cases at the level of its internal or hidden units. An analysis of the network’s internal representations is undertaken using a new visualization technique for state space approaches to understanding similarity. Insights from the literature on moral philosophy pertaining to contributory standards will be used to interpret the state space set up (...) by the ANN as being structured by implicit reasons. The ANN, on its own, is not capable of explicitly representing or offering reasons to itself or others. That said, the low level similarity space set up by the network could be made available to higher order processes that exploit it for case-based reasoning. It is argued that for normative purposes, similarity could be seen as a contributor to procedural coherence in case-based reasoning and local forms of substantive coherence, but not to global forms of coherence given the computational complexity of managing those more ambitious forms of coherence. (shrink)