Construct · 1 fields · 1 citations

random network distillation: 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.

Reinforcement learning (machine learning)

an exploration bonus equal to the error of a network trained to predict the outputs of a fixed random network on observed states.

In reinforcement learning (machine learning), random network distillation refers to an exploration bonus equal to the error of a network trained to predict the outputs of a fixed random network on observed states. This meaning comes from Burda (2018) in arXiv.[1]

Unit
Recovery means
Measured by

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

See how random network distillation 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

distillation3 fields · 6 citationsjingle · one word, three constructs error4 fields · 8 citationsjingle · one word, four constructs learning6 fields · 14 citationsjingle · one name, six constructs

References

Burda, Y., Edwards, H., Storkey, A., & Klimov, O. (2018). Exploration by Random Network Distillation. arXiv. https://doi.org/10.48550/arxiv.1810.12894

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