Дуэльные бандиты с несколькими руками
method
ID: multiarmedduelingbandits
Related Papers
Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering
AbstractIn this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation. To allow efficient adaptation, we cast the problem as a …...