Social Contracts for Non-Cooperative Games

Alan Davoust, Michael Rovatsos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In future agent societies, we might see AI systems engaging in selfish, calculated behavior, furthering their owners’ interests instead of socially desirable outcomes. How can we promote morally sound behaviour in such settings, in order to obtain more desirable outcomes? A solution from moral philosophy is the concept of a social contract, a set of rules that people would voluntarily commit to in order to obtain better outcomes than those brought by anarchy. We adapt this concept to a game-theoretic setting, to systematically modify the payoffs of a non-cooperative game, so that agents will rationally pursue socially desirable outcomes.

We show that for any game, a suitable social contract can be designed to produce an optimal outcome in terms of social welfare. We then investigate the limitations of applying this approach to alternative moral objectives, and establish that, for any alternative moral objective that is significantly different from social welfare, there are games for which no such social contract will be feasible that produces non-negligible social benefit compared to collective selfish behaviour.
Original languageEnglish
Title of host publicationAIES '20: Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society
PublisherAssociation for Computing Machinery (ACM)
Pages43-49
Number of pages7
ISBN (Print)9781450371100
DOIs
Publication statusPublished - 7 Feb 2020
EventThird AAAI/ACM Conference on Atrificial Intelligence, Ethics, and Society 2020 - New York, United States
Duration: 7 Feb 20208 Feb 2020
Conference number: 3
https://www.aies-conference.com/2020/

Conference

ConferenceThird AAAI/ACM Conference on Atrificial Intelligence, Ethics, and Society 2020
Abbreviated titleAIES 2020
CountryUnited States
CityNew York
Period7/02/208/02/20
Internet address

Keywords

  • Game theory
  • ethics
  • moral philosophy
  • agents

Cite this