TitleA structural solution to sequential moral dilemmas
Publication TypeConference Paper
Year of Publication2020
AuthorsRodríguez-Soto M, López-Sánchez M, Rodríguez-Aguilar JA
Conference NameInternational Conference on Autonomous Agents and Multi-Agent Systems
KeywordsGame theory for practical applications, Reinforcement Learning, safety, Values in multi-agent systems

Social interactions are key in multi-agent systems. Social dilem-

mas have been widely studied to model specific problems in social

interactions. However, state-of-the-art social dilemmas have dis-

regarded specific ethical aspects affecting interactions. Here we

propose a novel model for social dilemmas, the so-called

Sequential Moral Dilemmas, that do capture the notion of moral value. First,

we provide a formal definition of sequential moral dilemmas as

Markov Games. Thereafter, we formally characterise the necessary

and sufficient conditions for agents to learn to behave ethically, so

that they are aligned with the moral value. Moreover, we exploit our

theoretical characterisation to provide a structural solution

to a sequential moral dilemma, namely how to configure the Markov game

to solve the dilemma. Finally, we illustrate our proposal through

the so-called public civility game, an example of a sequential moral

dilemma considering the civility value. We show the social benefits

obtained when the agents learn to adhere to the moral value.