Value Learning

Intermediate

Inferring and aligning with human preferences.

Full Definition

Inferring and aligning with human preferences.

Keywords

human values

Domains

Governance & Ethics

Related Terms

Model Release Control related to

Restricting distribution of powerful models.

 Alignment Research related to

Research ensuring AI remains safe.

 Differential Progress related to

Accelerating safety relative to capabilities.

 Cooperative AI related to

Designing AI to cooperate with humans and each other.

Concept Map

See how Value Learning connects to other concepts.

Open Knowledge Graph