Although virtue ethics has repeatedly been proposed as a suitable framework for the development of artificial moral agents, it has been proven difficult to approach from a computational perspective. In this work, we present the first technical implementation of artificial virtuous agents in moral simulations. First, we review previous conceptual and technical work in artificial virtue ethics and describe a functionalistic path to AVAs based on dispositional virtues, bottom-up learning, and top-down eudaimonic reward. We then provide the details of a (...) technical implementation in a moral simulation based on a tragedy of the commons scenario. The experimental results show how the AVAs learn to tackle cooperation problems while exhibiting core features of their theoretical counterpart, including moral character, dispositional virtues, learning from experience, and the pursuit of eudaimonia. Ultimately, we argue that virtue ethics provides a compelling path toward morally excellent machines and that our work provides an important starting point for such endeavors. (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)

This work is an investigation into philosophical method and rational argument in moral philosophy. It makes an original contribution to human understanding, by taking some of the tools and techniques that Gordon Baker identifies in the later work of Wittgenstein, and using them as a way of fending for oneself in an area of philosophy that neither Baker, nor Wittgenstein, wrote on. More specifically, a discussion of some different aspects of the contemporary literature on Dancy’s moral particularism is used as (...) a vehicle for illustrating how Baker’s therapeutic conception of philosophy offers alternative possibilities for how we can do philosophy, and what counts as rational argument in moral philosophy. I maintain that, by considering some indicative ways in which Baker’s therapeutic approach to philosophy can dissolve, rather than solve, the kinds of perplexities found in the existing literature on Dancy’s moral particularism, we can liberate ourselves from the traditional/theoretical view of how we ought to do philosophy, and an understanding of rational argument in moral philosophy, to which we need not be committed. (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)