Treffer: MABSearch: The Bandit Way of Learning the Learning Rate—A Harmony Between Reinforcement Learning and Gradient Descent
Title:
MABSearch: The Bandit Way of Learning the Learning Rate—A Harmony Between Reinforcement Learning and Gradient Descent
Authors:
Syed Shahul Hameed, A. S.Aff1, IDs40009023012921_cor1, Rajagopalan, Narendran
Source:
National Academy Science Letters. :1-6
Database:
Springer Nature Journals