Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
FraPPE: Fast and Efficient Preference-based Pure Exploration
Udvas Das, Apurv Shukla, Debabrota Basu
Preference-based Pure Exploration (PrePEx) aims to identify with a given confidence level the set of Pareto optimal arms in a vector-valued (aka multi-objective) bandit, where the…
cs.LG2025
Vector preference-based contextual bandits under distributional shifts
Apurv Shukla, P. R. Kumar
We consider contextual bandit learning under distribution shift when reward vectors are ordered according to a given preference cone. We propose an adaptive-discretization and opti…