Learnability of adversarial noisy bandits is characterized by the convexified generalized maximin volume for oblivious adversaries and for adaptive adversaries when the arm space is countable.
36th International Conference on Algorithmic Learning Theory , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On Characterizing Learnability for Adversarial Noisy Bandits
Learnability of adversarial noisy bandits is characterized by the convexified generalized maximin volume for oblivious adversaries and for adaptive adversaries when the arm space is countable.