Abstract

Modelling ethics is critical to understanding and analysing social phenomena. However, prior literature either incorporates ethics into agent strategies or uses it for evaluation of agent behaviour. This work proposes a framework that models both, ethical decision making as well as evaluation using virtue ethics and utilitarianism. In an iteration, agents can use either the classical Continuous Prisoner's Dilemma or a new type of interaction called moral interaction, where agents donate or steal from other agents. We introduce moral interactions to model ethical decision making. We also propose a novel agent type, called virtue agent, parametrised by the agent's level of ethics. Virtue agents' decisions are based on moral evaluations of past interactions. Our simulations show that unethical agents make short term gains but are less prosperous in the long run. We find that in societies with positivity bias, unethical agents have high incentive to become ethical. The opposite is true of societies with negativity bias. We also evaluate the ethicality of existing strategies and compare them to those of virtue agents.