Search Results for author:
Found 4 papers, 0 papers with code
Social learning via actions in bandit environments
I study a game of strategic exploration with private payoffs and public actions in a Bayesian bandit setting.
Risk Preferences of Learning Algorithms
The first method requires the algorithm to reweight data as a function of how likely the actions were to be chosen.
Single-peaked domains with designer uncertainty
This paper studies single-peaked domains where the designer is uncertain about the underlying alignment according to which the domain is single-peaked.
Ex-post implementation with interdependent values
We characterize ex-post implementable allocation rules for single object auctions under quasi-linear preferences with convex interdependent value functions.
