DeepMellow: Removing the Need for a Target Network in Deep Q-Learning.

Seungchan Kim Kavosh Asadi Michael L. Littman George Dimitri Konidaris

Published in: IJCAI (2019)

Keyphrases

cooperative
learning algorithm
wireless sensor networks
network topologies
reinforcement learning
multi agent
peer to peer
complex networks
function approximation
network management
machine learning
social networks
link prediction
action selection