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.

翻译：伦理人工智能领域面临的主要挑战之一，是开发推理和行为可证明与人类价值观对齐的计算系统。然而，人类价值观以模糊、矛盾且不断变化而著称。为弥合这一差距，并推动我们更接近能够形式化推理价值观在人工智能中实现的境地，本文提出了一种基于社会科学的形式化价值观表示。我们利用这种形式化表示，阐明了在多智能体系统中实现价值观对齐行为的关键挑战，以及应对这些挑战的研究路线图。