Construct · 1 fields · 1 citations

actor-critic: 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.

Computational neuroscience

a learning architecture in which a critic estimates value and its prediction error trains an actor that selects actions.

In computational neuroscience, actor-critic refers to a learning architecture in which a critic estimates value and its prediction error trains an actor that selects actions. This meaning comes from Barto (1983) in IEEE Transactions on Systems, Man, and Cybernetics.[1]

Unit
Recovery means
Measured by

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

See how actor-critic 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

cart-pole balancing problem1 fields · 1 citationsanchor · a standalone construct architecture3 fields · 4 citationsjingle · one word, three constructs asynchronous advantage actor-critic1 fields · 1 citationsanchor · a standalone construct

References

Barto, A. G., Sutton, R. S., & Anderson, C. W. (1983). Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Transactions on Systems, Man, and Cybernetics, SMC-13(5), 834-846. https://doi.org/10.1109/tsmc.1983.6313077

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