What is it about?
This article presents a decision model that allows autonomous intelligent agents to choose actions that align with their value system. It considers the importance of different values to an agent and how much an action advances a particular value. Additionally, it rigorously models the interaction of different values within a value system.
Featured Image
Photo by Michael Dziedzic on Unsplash
Why is it important?
This work is important because the proposed model allows the agent to act based on the interaction between human values based on Schwartz's theory of basic human values. In this way, the agent can evaluate how its decisions impact the environment and adapt them according to the order of preferences over the represented values.
Perspectives
The next steps involve studying groups of agents with similar value systems interaction. In this way, to establish how human values affect the behaviour of agent societies.
Marcelo Javier Karanik
Universidad Rey Juan Carlos
Read the Original
This page is a summary of: On the relevance of value system structure for automated value-aligned decision-making, April 2024, ACM (Association for Computing Machinery),
DOI: 10.1145/3605098.3636057.
You can read the full text:
Contributors
The following have contributed to this page
