Under four structural conditions linking proxy and true preference policies, the true policy is a low-dimensional adapter of the proxy policy, reducing the number of true preference samples needed.
The evolved radio and its implications for modelling the evolution of novel sensors
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
When Can Proxies Improve the Sample Complexity of Preference Learning?
Under four structural conditions linking proxy and true preference policies, the true policy is a low-dimensional adapter of the proxy policy, reducing the number of true preference samples needed.