The paper gives epoch explore-then-commit algorithms with regret bounds for utilitarian-optimal and maximin stable matching in two-sided bandit markets, but the maximin algorithm appears to solve a different objective.
Two-sided bandits and the dating market
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2024 1verdicts
REJECT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Bandit Learning in Matching Markets: Utilitarian and Rawlsian Perspectives
The paper gives epoch explore-then-commit algorithms with regret bounds for utilitarian-optimal and maximin stable matching in two-sided bandit markets, but the maximin algorithm appears to solve a different objective.