A new algorithm for the incomplete-information game of coding learns adversary preferences through repeated interactions and achieves sublinear cumulative regret by focusing search on promising acceptance rules.
Nearly tight bounds for the continuum-armed ban- dit problem
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IT 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Learning from Acceptance: Cumulative Regret in the Game of Coding
A new algorithm for the incomplete-information game of coding learns adversary preferences through repeated interactions and achieves sublinear cumulative regret by focusing search on promising acceptance rules.