Exploring Affinity-Based Reinforcement Learning for Designing Artificial Virtuous Agents in Stochastic Environments

Abstract

Artificial virtuous agents are artificial intelligence agents capable of virtuous behavior. Virtues are defined as an excellence in moral character, for example, compassion, honesty, etc. Developing virtues in AI comes under the umbrella of machine ethics research, which aims to embed ethical theories into artificial intelligence systems. We have recently suggested the use of affinity-based reinforcement learning to impart virtuous behavior. Such a technique uses policy regularization on reinforcement learning algorithms, and it has advantages such as interpretability and convergence properties. Hence, we evaluate the efficacy of affinity-based reinforcement learning to design artificial virtuous agents using a stochastic role-playing game environment. Our results show that virtuous behavior can indeed result in our Papers, Please environment, and that algorithmic convergence can be controlled by the relevant hyperparameters. We then discuss some insights from our empirical evaluation of this method and motivate future research directions.