OTO balances lower-confidence-bound and upper-confidence-bound play in offline-to-online bandits and matches the better of the two in regret, up to log factors and an additive budget term.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Balancing optimism and pessimism in offline-to-online learning
OTO balances lower-confidence-bound and upper-confidence-bound play in offline-to-online bandits and matches the better of the two in regret, up to log factors and an additive budget term.