Human Values in Multiagent Systems Article Swipe

PDF

Related Concepts

Bridge (graph theory) Representation (politics) Computer science Face (sociological concept) Value (mathematics) Key (lock) Order (exchange) Management science Artificial intelligence Epistemology Data science Sociology Political science Engineering Social science Business Machine learning Philosophy Computer security Finance Medicine Politics Internal medicine Law

Nardine Osman , Mark d’Inverno ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2305.02739 · OA: W4372278798

One of the major challenges we face with ethical AI today is developing computational systems whose reasoning and behaviour are provably aligned with human values. Human values, however, are notorious for being ambiguous, contradictory and ever-changing. In order to bridge this gap, and get us closer to the situation where we can formally reason about implementing values into AI, this paper presents a formal representation of values, grounded in the social sciences. We use this formal representation to articulate the key challenges for achieving value-aligned behaviour in multiagent systems (MAS) and a research roadmap for addressing them.