Construct · 1 fields · 1 citations

value learning: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

AI safety

designing an agent that learns which outcomes to value from evidence, rather than having a fixed utility function specified in advance.

In AI safety, value learning refers to designing an agent that learns which outcomes to value from evidence, rather than having a fixed utility function specified in advance. This meaning comes from Dewey (2011) in Lecture Notes in Computer Science.[1]

Unit
Recovery means
Measured by

Run it through the Collider, or take the citations with you.

See how value learning sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in Collider Export BibTeX Report this entry

Nearby constructs

agent3 fields · 5 citationsjingle · one word, three constructs evidence2 fields · 4 citationsjingle · one word, two constructs function5 fields · 6 citationsjingle · one word, five constructs

References

Dewey, D. (2011). Learning What to Value. In Lecture Notes in Computer Science (pp. 309-314). Springer Berlin Heidelberg. https://doi.org/10.1007/978-3-642-22887-2_35

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct