research
∙
09/15/2023
Price of Safety in Linear Best Arm Identification
We introduce the safe best-arm identification framework with linear feed...
share
research
∙
03/01/2021
UCB Momentum Q-learning: Correcting the bias without forgetting
We propose UCBMQ, Upper Confidence Bound Momentum Q-learning, a new algo...
research
∙
10/15/2020
Stochastic Bandits with Vector Losses: Minimizing ℓ^∞-Norm of Relative Losses
Multi-armed bandits are widely applied in scenarios like recommender sys...
research
∙
07/02/2020
Gamification of Pure Exploration for Linear Bandits
We investigate an active pure-exploration setting, that includes best-ar...
research
∙
10/24/2019