Artificial virtuous agents in a multiagent tragedy of the commons
arXiv:2210.02769 · doi:10.1007/s00146-022-01569-x
Abstract
Although virtue ethics has repeatedly been proposed as a suitable framework for the development of artificial moral agents (AMAs), it has been proven difficult to approach from a computational perspective. In this work, we present the first technical implementation of artificial virtuous agents (AVAs) 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.
arXiv comment18 pages, 5 figures, 3 tables. AI & SOCIETY (2022)
References in corpus (6)
- Dota 2 with Large Scale Deep Reinforcement Learning
- Artificial Intelligence, Values and Alignment
- Reward and cooperation in the spatial public goods game
- Evolutionary establishment of moral and double moral standards through spatial interactions
- Implementations in Machine Ethics: A Survey
- Reinforcement Learning Your Way: Agent Characterization through Policy Regularization