Reinforcement Learning and Machine ethics:a systematic review

TL;DR

This paper systematically reviews how reinforcement learning is used to develop ethical behavior in autonomous systems, highlighting recent trends, frameworks, and environments in this emerging research area.

Contribution

It consolidates recent work on reinforcement learning in machine ethics, addressing a gap in prior reviews and identifying key trends and components in the field.

Findings

Increase in reinforcement learning studies focused on ethics since 2020

Identification of common ethics specifications and frameworks

Analysis of environments used for ethical reinforcement learning

Abstract

Machine ethics is the field that studies how ethical behaviour can be accomplished by autonomous systems. While there exist some systematic reviews aiming to consolidate the state of the art in machine ethics prior to 2020, these tend to not include work that uses reinforcement learning agents as entities whose ethical behaviour is to be achieved. The reason for this is that only in the last years we have witnessed an increase in machine ethics studies within reinforcement learning. We present here a systematic review of reinforcement learning for machine ethics and machine ethics within reinforcement learning. Additionally, we highlight trends in terms of ethics specifications, components and frameworks of reinforcement learning, and environments used to result in ethical behaviour. Our systematic review aims to consolidate the work in machine ethics and reinforcement learning thus completing the gap in the state of the art machine ethics landscape