Construct · 1 fields · 1 citations

reinforcement learning from human feedback: 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

training an agent against a reward model fitted to human comparisons between pairs of its behaviors, instead of a hand-written reward function.

In ai safety, reinforcement learning from human feedback refers to training an agent against a reward model fitted to human comparisons between pairs of its behaviors, instead of a hand-written reward function. This meaning comes from Christiano (2017) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how reinforcement learning from human feedback 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 alignment6 fields · 12 citationsjingle · one name, six constructs feedback4 fields · 5 citationsjingle · one word, four constructs

References

Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017). Deep reinforcement learning from human preferences. arXiv. https://doi.org/10.48550/arxiv.1706.03741

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