Search Results for author: Thomas Donaldson

Found 3 papers, 0 papers with code

Taking Principles Seriously: A Hybrid Approach to Value Alignment

no code implementations21 Dec 2020 Tae Wan Kim, John Hooker, Thomas Donaldson

An important step in the development of value alignment (VA) systems in AI is understanding how VA can reflect valid ethical principles.

Grounding Value Alignment with Ethical Principles

no code implementations11 Jul 2019 Tae Wan Kim, Thomas Donaldson, John Hooker

The second problem is that AI designers adopt training routines that fail fully to simulate human ethical reasoning in the integration of ethical principles and facts.

Mimetic vs Anchored Value Alignment in Artificial Intelligence

no code implementations25 Oct 2018 Tae Wan Kim, Thomas Donaldson, John Hooker

"Value alignment" (VA) is considered as one of the top priorities in AI research.

Cannot find the paper you are looking for? You can Submit a new open access paper.