Reinforcement Learning and Machine ethics:a systematic review
It addresses the problem of understanding ethical behavior in RL systems for researchers and practitioners, but it is incremental as it builds on existing reviews by adding RL-specific coverage.
This paper tackles the gap in systematic reviews of machine ethics by focusing on reinforcement learning (RL) agents, consolidating recent work to complete the state of the art landscape.
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