The authors formalize Best Group Identification in multi-objective bandits and give elimination algorithms with upper and lower sample-complexity bounds for Pareto and linear objectives.
Pure exploration in multi-armed bandits problems
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
-
Best Group Identification in Multi-Objective Bandits
The authors formalize Best Group Identification in multi-objective bandits and give elimination algorithms with upper and lower sample-complexity bounds for Pareto and linear objectives.