Finite-time theory for momentum Q-learning.

Bowen Weng Huaqing Xiong Lin Zhao Yingbin Liang Wei Zhang

Published in: UAI (2021)

Keyphrases

learning rate
function approximation
formal theory
reinforcement learning
multi agent
theoretical framework
theoretical basis
action selection
stochastic approximation
database
data sets
information retrieval
learning algorithm
knowledge base
finite number
equational theories