Algorithms for lexicographic multiobjective bandits achieve bounded expected regret with partial prior knowledge of optimal rewards per objective and sublinear gap-free regret in the prior-free case.
Designing multi-objective multi-armed bandits algorithms: A study,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Lexicographic Multiarmed Bandit
Algorithms for lexicographic multiobjective bandits achieve bounded expected regret with partial prior knowledge of optimal rewards per objective and sublinear gap-free regret in the prior-free case.